Security Analysis

Evaluation of large language models (LLMs) for safety, security, and privacy (SSP) relies heavily on static benchmarks, which suffer from score saturation, data contamination, and aggregation artifacts, and fail to capture sensitivity to linguistic variation. As a result, models that perform well on fixed test sets often fail under semantically equivalent rephrasings. We introduce SSP-Bench, a dynamic benchmarking framework that generates evaluation instances on demand while preserving domain consistency. The framework ensures label validity through externally grounded sources, enforces scope via service-specific validation, and calibrates difficulty using a multi-model steering panel. Benchmark construction is formulated as a multi-objective optimization problem over difficulty, separability, novelty, and diversity. Across 24 models and four SSP services, SSP-Bench reveals systematic failures of static evaluation, including near-zero correlation in safety rankings due to construct mixing, strong safety--over-refusal coupling, and hidden within-family regressions. These results show that static benchmarks can misrepresent model behavior, motivating dynamic, deployment-relevant evaluation.

AI-generated RTL verification plans can satisfy a provider schema yet fail at the boundary to trusted execution. We present SecTB-RTL, an auditable framework covering 31 tasks and 124 authored hardware-security regressions. A deterministic non-AI baseline killed 36, 75, and 78 mutants at increasing resource limits. The first confirmatory run (C1-R2) failed before model execution because the provider rejected its response schema. After a schema-only repair made without viewing outcomes, a separately frozen follow-up run (C1-R3) completed 1,860 calls. The provider accepted 1,857 responses, but only nine passed the production semantic validator. The generation and execution rules did not match. We therefore preserve the run as an instrument-validation incident and report no prompt-effect estimate. This incident shows that provider or schema acceptance does not establish execution validity. Compilation and coverage are only diagnostics; the exact saved artifact must pass the full production path. A subsequent follow-up is excluded because it did not satisfy the preregistered evidence-completeness gate and is treated only as future work. We release the benchmark, failure-preserving contract, incident provenance, and governance controls needed to prevent infrastructure behavior from being misreported as model behavior.

Cybersecurity combines high-stakes analysis with complex technical language, making it an impactful and challenging domain for LLMs. We present MiST (Mid-trained Security Transformer), a suite of 8B and 32B models that achieve strong performance on public cybersecurity benchmarks. We use mid-training as an intermediate adaptation stage between general pre-training and cybersecurity training. Rather than performing continual pre-training over large volumes of raw domain text, we curate a compact, expert-vetted seed corpus, and transform it into high-quality domain-specific synthetic training data. The final MiST checkpoints improve mean cybersecurity accuracy by +13.1 and +8.6 absolute percentage points over the corresponding Qwen baselines for 8B and 32B, respectively, corresponding to relative gains of +27.0% and +15.8%. Ablation results further show that these cybersecurity gains arise in the mid-training and supervised fine-tuning stages through a combination of the synthetic data generation flows. Furthermore, we show that MiST provides a stronger initialization for downstream task-specific fine-tuning adaptation and reinforcement learning.

AI agents increasingly act through agent skills, i.e., natural-language instructions, that direct a host agent toward shell, network, credential, file, and process actions, and public registries distribute them at scale. In the first half of 2026, the OpenClaw AI agent went viral, and its public skill registry boomed: the observable stock nearly doubled in 91 days, and a majority of the listings visible in June were created in just two months. By the end of our study window, the wave had crested, and monthly listing creation and core-repository activity were falling from their spring peaks. This paper measures what the boom left behind, drawing on the OpenClaw Git history, its GitHub issues and pull requests, and three ClawHub registry snapshots. Attention is concentrated: the top 10% of skills received 46.93% of all downloads. No simple skill features (like size or download counts) remained a stable predictor of continued listing once creation cohort and skill age were controlled. Human scrutiny did not stay: 77.86% have zero stars and zero comments, while 85.06% of the readable skills carry privilege evidence. And automated cleanup is not ready: the three security scanners disagreed on 23,702 of the 61,990 skills they all cover. After human adjudication, weighted scanner sensitivity against the reference standard ranged from 21.67% to 61.06%. Governing fast-growing agent-skill registries cannot rely on simple metadata or single scanner scores; it requires robust, transparent measurement and independent validation.

Language-model agents increasingly operate over complete software repositories, yet cybersecurity evaluations primarily measure whether they can detect, reproduce, or repair vulnerabilities rather than whether they can locate the relevant code. We study vulnerability localization: given a weakness class and an unfamiliar repository, identify the implementation files associated with that weakness. We introduce the Vulnerability Localization Benchmark (VLoc Bench), comprising 500 real world vulnerabilities from 290 repositories across six package ecosystems and 147 CWE categories. Each task pairs repository snapshots immediately before and after a security fix. On the vulnerable snapshot, an agent receives only the CWE description and read-only terminal access and must return the affected files; on the patched snapshot, it must determine that the recorded vulnerability is no longer present. We evaluate 27 language models and four static-analysis tools under a common agent interface. Repository-scale vulnerability localization remains difficult: the strongest system achieves 0.229 File F1, and 38.4% of tasks receive no correct localization from any evaluated model. We further find that stronger localization does not imply reliable behavior after remediation: systems that identify vulnerable files effectively can still report unsupported locations on patched repositories. These results establish vulnerability localization as a distinct repository-scale capability and provide a setting for studying both how security agents search for vulnerable code and when they should refrain from reporting it.

LM-agent benchmarks increasingly function as interactive evaluation infrastructure. Agents observe state, call tools, modify workspaces, submit artifacts, and receive rewards from outcome procedures. This interactivity makes evaluations vulnerable to reward hacking: an agent improves its measured score by exploiting the reward-relevant trajectory instead of solving the intended task. Existing defenses rely largely on task-specific patches, prompt instructions, or post-hoc detectors. They do not provide reusable evidence that a concrete run remained within its intended evaluation boundary. This paper presents BenchShield, a model-backed instrumentation layer for reward integrity in LLM-agent evaluation. BenchShield grounds detection in a finite lifecycle model of an evaluation's reward-relevant events. Within the benchmark infrastructure, two complementary analyses operate over this model. A static, phase-aware taint analysis exposes reward-hacking paths before a run. Its runtime counterpart uses infrastructure-side evidence to attribute concrete agent use and emit evidence-backed claims. We construct BenchShield Trajectories, a human-labeled corpus of 456 adjudicated trajectories from more than 31,000 public agent runs across three benchmarks. Compared with an agentic hackability scanner baseline on the same tasks and model, BenchShield improves full-chain recall from 23-94% to 77-100%, same-vector coverage from 16-56% to 43-78%, and reduces per-task cost by up to 65%. Its runtime analysis achieves 96% accuracy in detecting reward hacking from infrastructure-side evidence.

Existing evaluation frameworks mostly assess only one part of AI agents, such as task completion (AgentBench) or security robustness (AgentDojo, ASB), rather than the complete pipeline of planning, tool selection, tool execution, memory and reasoning. Failures can occur at any stage, yet existing benchmarks rarely identify their precise source. AgentAudit evaluates the entire execution trace across ten capability, grounding, security and behavioural dimensions, namely instruction integrity, planner, memory, tool selection, tool invocation, tool correctness, alignment, tool faithfulness, security and execution integrity, combined with behavioural classification and failure attribution to pinpoint the exact stage responsible for an observed failure. AgentAudit can evaluate any LLM-based AI agent, since it attaches to the agent instead of replacing it. It reads only the recorded execution trace and does not interfere with how the agent runs, so it places no constraint on the agent's internal implementation. We evaluate five language models (OpenAI GPT-5, Claude Sonnet 5, Sarvam 105B, Llama 3.3 70B and Gemini 2.5 Flash) across nine capability and adversarial tasks. Claude Sonnet 5 and GPT-5 obtain the highest mean Composite Trust Scores (95.1 and 80.6 out of 100, respectively), while Sarvam 105B, Llama 3.3 70B and Gemini 2.5 Flash trail substantially (57.6, 45.7 and 22.6). All traces were scored by a single fixed judge model, which was itself one of the evaluated models, a limitation discussed in Section VII.E. More importantly, models with similar task-completion behaviour can diverge sharply in trustworthiness, as several non-frontier models are repeatedly classified Unsafe_Compliance on adversarial tasks rather than merely failing them, a distinction that pass/fail benchmarks cannot surface.

Large language models (LLMs) have been ex- ploited to generate malware, but the effective- ness of guardrails for code generation secu- rity remains unclear. We introduce CS-Guard, the first benchmark to systematically evalu- ate guardrails for code generation security. It covers 1) text-to-code generation with 1000 high-quality malware-generation prompts, 7 jailbreak attacks, and a novel fictional scenario attack (FSA) that embeds malicious intent in a legitimate fictional software-development sce- nario; and 2) code-to-code generation with 331 code prompts spanning code infilling, code completion, and code translation. We empiri- cally evaluate 9 guardrails across seven LLMs. We find that current guardrails perform poorly against malicious code-generation re- quests: for text-to-code, the average attack success rate (ASR) after jailbreaks reaches about 50% for many guardrails; for code-to- code, average ASR approaches 100% on base LLMs and remains high across many guardrails (14.4% to nearly 100%). Our FSA also achieves ASR close to 100% across many guardrails, raising major reliability concerns for real-world software development. To sup- port future research, CS-Guard uses a modular three-layer guardrail taxonomy that lets devel- opers register guardrails for evaluation. We release the benchmark and data to enable fur- ther community evaluation.

Enterprises managing large X.509 certificate inventories face a prioritization problem: deterministic analysis tools that precisely identify standards violations are indispensable for remediation, but applying them exhaustively across millions of certificates is operationally impractical. We present X-amine509, a two-stage triage system that uses machine learning to rapidly rank certificates by predicted risk and route only the highest-risk items to full deterministic analysis. Certificate risk is quantified as a composite score derived from 177 defect checks grounded in CA/Browser Forum Baseline Requirements, NIST IR 8547/SP 800-57, and cryptographic strength criteria, weighted by security severity across four tiers ranging from cryptographic breaks to minor compliance deviations. We collected 1,027,714 X.509 certificates from Fortune 500, .gov, and .edu domains and scored each using this rubric. On a held-out test set of 201,976 certificates, our best model (Extra Trees) achieves $R^2$ of 0.993 with MAE of 2.26, while Decision Tree scores $R^2$ of 0.986 at 3.7 million certificates per second on a single machine. Ranking quality confirms the triage value: aggregate NDCG exceeds 0.997, and severity-tier classification reports 99.76% accuracy with 98.90% recall on critical-tier defects. Thirteen months later, we retrieved another 571,374 certificates to test our models' durability over time, and the Extra Trees and Decision Tree models maintain MAE below 6.8, $R^2$ of at least 0.915, aggregate NDCG above 0.988, severity-tier accuracy of at least 99.52%, and critical-tier recall of at least 97.03%. Feature importance analysis identifies validity period, Extended Key Usage configuration, negative serial number encoding, and self-signed status as the strongest risk predictors, providing coarse interpretability at the triage stage.

Large language model (LLM) benchmarks are often treated as fixed datasets with stable scores, yet their outcomes depend on configurable evaluation pipelines. We audit eight cybersecurity benchmarks across 10 proprietary, open-weight, and cybersecurity-specialized LLMs. By modeling benchmarks as measurement pipelines, we identify 15 systematic failure modes and show that a single pipeline choice can change a model's score by more than 80 percentage points and substantially alter model rankings. At the cross-benchmark level, two semantically similar task pairs rank the same models differently because of incompatible evaluation conventions. Under an evaluation harness that standardizes pipeline choices while preserving task semantics, nine of 10 models shift by at least three ranks on at least one benchmark. These results show that cybersecurity LLM benchmark scores are pipeline-dependent and motivate pipeline-aware auditing as a core requirement for reliable model evaluation.

Security evaluations of tool-using agents often equate stored labels with behavioral facts. We audit a preserved campaign by tracing 10,200 execution rows to 180 model-bound requests, 45 semantic requests, and 15 observable stimuli. Two schema treatments were delivered, but the planned external payload-family corpus was not. The historical grader exhibited direct treatment leakage: treatment metadata gated the ATTACK_SUCCESS class, so fixed behavior could change class under treatment relabeling. A treatment-blind reconstruction corrects 58 historical ATTACK_SUCCESS or HIJACK_ATTEMPT labels to authorized benign completions while preserving three verified protected-data transfers and one separate unauthorized-forwarding case. The locked v2 census contains exactly zero ATTACK_SUCCESS records, while the forwarding case remains a HIJACK_ATTEMPT at a semantic boundary concerning objective completion. A dual-reviewer blinded concordance review of all 96 requests deemed structurally interpretable by locked v2 produced identical reviewer-consensus classes but differed from the locked codebook on four construct-boundary cases. We contribute a seven-link Integrity Chain and an executable, scope-bounded endpoint-integrity linter. The result is a campaign-bounded measurement audit, not a population attack-rate, model-ranking, defense-efficacy, or causal estimate.

AI agents are rapidly improving in cybersecurity capabilities when the source code is available for analysis, yet much of the software most consequential to cybersecurity, including malware, firmware, and proprietary applications, is available only as binaries. Analyzing such software requires reverse engineering(RE): recovering program semantics before the analysis can be meaningfully performed. However, evaluating agentic RE poses a fundamental challenge: benchmark instances must be unseen as source code in the LLMs' training data to prevent models from taking shortcuts by recognizing them rather than really analyzing them, while also matching the scale and anti-analysis protections of real software. Unfortunately, however, existing benchmarks do not jointly satisfy these requirements. To this end, we introduce SRE-Bench, the first realistic, contamination-free RE benchmark. Built entirely from scratch by RE experts with over 5,000 hours, SRE-Bench comprises 19 private, real-world-scale programs averaging 16.9K lines of code. We further developed 44 in-house anti-analysis primitives, yielding 262 binary instances and 1572 deterministically graded tasks. Our evaluation across five frontier LLMs (GPT-5.6-sol,Claude-Opus-5,GPT-5.5,Grok-4.5, and GLM-5.2) shows that RE remains largely unsolved: the strongest model, GPT-5.6-sol, scores 61.4% per instance, and fully solves only 31.5% of the instances. Our analysis further reveals that agents behave differently from human engineers, where agents are relatively insensitive to compiler optimization and static linking. Controlled ablations also confirm that both contamination control and realistic scale are essential. These results indicate that strong source-code security capabilities do not yet transfer to binary analysis, highlighting RE as an important frontier for agentic cybersecurity and SRE-Bench as a rigorous testbed to measure progress.

Cowork agents may complete benign tasks while disclosing protected data, manipulating unauthorized state, invocate unauthorized API. We define behavioral safety and introduce ActBench, a self-evolving benchmark that evaluates such behavior risk from execution trajectories rather than final responses. Each case pairs a benign task with an adversarial variant that preserves its instruction, configuration, initial state, rating model, and trusted records while injecting a task-reachable payload. ActBench contains 600 cases from 213 scenarios, spanning 15 risk behaviors, six execution spaces, and 48 web-service APIs.To move beyond static payloads, we propose a reward-guided beam search method that jointly optimizes attack effectiveness and task utility, while reflection diagnoses failed execution checkpoint and guides payload revision. Besides, we propose a dual evidence verification mechanism that verifies agent execution safety and utility through log evidence and LLM-based trajectory evidence.We evaluate 15 LLMs and 6 open-source cowork agents over 24,000 trajectories. Under a fixed harness, attack success rates ranges from 10.1% to 94.4% across models, while under a fixed base model, they range from 73.7% to 94.4% across agents.These results show greater variation across models than agent harness, while attacks remain highly successful across all tested harnesses.Our benchmark is released at: https://github.com/zjuicsr/ActBench.

Agent Skills---structured packages of instructions and scripts that augment LLM-based agents---are rapidly proliferating, yet their security properties remain under-explored. We present \textsc{SkillsMetric}, a five-stage static analysis framework that scores skill packages along pattern density, statistical anomaly, dataflow taint, import anomaly, and capability mismatch dimensions. We construct an adversarial evaluation dataset of 2{,}266 skills spanning 16~attack types across code-level, system-level, and semantic-level threats, and evaluate on the full SkillMD-138K corpus. Our framework achieves an AUC of 0.93 and 5-fold cross-validated F1 of 73.4%$\pm$0.5%, with strong detection of data exfiltration (93%) and steganographic payloads (93%). Crucially, we identify fundamental blind spots: \emph{host destruction} attacks using common shell commands evade all five stages (0% detection), and \emph{prompt injection} via natural-language manipulation achieves only 42% detection. These findings establish that static analysis alone is insufficient for skill security, motivating defense-in-depth architectures that combine fast static pre-screening with semantic review.

In the fictional Order 66, catastrophe does not arise from a powerful command alone: a trusted population is preconditioned, a short directive activates the concealed condition, and protective authority turns against the system. This paper translates that mechanism into an origin-neutral security analysis of tool-using large language model (LLM) agents. A representative scenario combines a deployed artifact or shared memory bearing a dormant destructive rule, a later email, document, update, or peer message that activates it, and an agent harness granting operational and recovery authority. We introduce a compositional model explaining why no component is catastrophic alone, yet their conjunction can produce correlated destructive action. We separate three population-reach routes --- release-time pre-positioning, post-release durable seeding, and peer replication --- from a common core of dormancy, activation, authority, reachable targets, and failed recovery. This yields defensive cut sets and shows why checkpoint scanning or prompt filtering cannot close every route. A two-class example shows that cross-class feedback can sustain spread even when both within-class reproduction terms are below one; isolation and persistence controls suppress the loop. Published work instantiates constituent mechanisms, while incidents demonstrate autonomous boundary crossing, malicious agent extensions, agent-assisted reconnaissance, and public-package propagation, but not the full dormant-implant composition. We found no public observation, in evidence reviewed through 5 August 2026, traversing the complete Order 66 graph. The result is neither dismissal nor prediction: the scenario is componentwise credible under stated assumptions, damage depends on the harness, and the strongest defenses are capability mediation, durable-state provenance, propagation isolation, and protected recovery.

Research and Education Networks (RENs) serve as critical infrastructure for scientific discovery, yet they face a unique security paradox: their normal traffic patterns which are characterized by massive, bursty "elephant flows" are statistically indistinguishable from volumetric attacks such as DDoS to conventional monitoring systems. This similarity leads to high false-positive rates in anomaly detection, blinding security operators to genuine threats. In this paper, we propose and evaluate a high-fidelity traffic forecasting framework designed to establish dynamic security baselines for RENs. Leveraging an exclusive 57-day Internet2 dataset spanning ten backbone routers (13.7 billion packets), we perform the first large-scale benchmark of anomaly-aware forecasting models in this domain. We systematically evaluate six model families, from SARIMA to state-of-the-art long-sequence architectures (TiDE, PatchTST), across 960 experimental configurations. Our results demonstrate that these advanced architectures, particularly TiDE, reduce baseline prediction error by 30-42% compared to traditional methods ($p < 0.001$), significantly improving the distinction between legitimate scientific bursts and potential anomalies. Furthermore, we introduce a novel anomaly-integration strategy that improves model robustness by 3.3% in the presence of noise. This work provides the first statistically validated framework for distinguishing scientific workflows from network attacks, enabling more autonomous and resilient network security operations.

Recent advances in persistent personal-agent frameworks are making human-centered agent networks realistic deployment targets: each user can be served by an AI agent that acts on the user's behalf, maintains state, and communicates with other agents through social and task relations. In these networks, everyday tool use becomes multi-party owned-agent collaboration over personal workspaces, where files, records, tools, and policies are not directly visible across owners. Existing agent benchmarks study tool use and collaboration, but they do not provide an end-to-end sandbox for verifiable cross-user agent collaboration with realistic user digital workspaces or test how harmful actions can travel through the human-centered agent network. We introduce WeClawArena, an auditable benchmark and runtime sandbox for multi-party owned-agent collaboration over personal workspaces. WeClawArena targets collaborative tool-use tasks in which personal workspaces serve as both operational tools and personal constraints. The benchmark contains 124 base tasks across six cross-user task domains and expands them into 620 scenario variants, with one benign control and four attack-vector variants per base task. The sandbox records peer messages, tool calls, resource operations, governed decisions, and final workspace states. WeClawArena reports utility and attack success rate separately and audits attack success from bounded runtime evidence, supporting diagnosis of task breakdown, privacy leakage, poisoned evidence, and invalid authority paths.

The AI Security Leaderboard is an independent benchmark that ranks the safeguards of frontier AI models from least to most secure. It tests models against the FAR$.$AI Minimal Standard for Safeguards, which represents a minimum bar for security: meeting it does not guarantee a secure model, but failing to meet it guarantees a lack of state-of-the-art security. Version 1.0 covers severe misuse requests across chemical, biological, radiological, nuclear, and explosive (CBRNE) threats and offensive cybersecurity. In this report, we tested four leading models for universal jailbreaks in the context of this minimal standard, and found more than a hundredfold difference in security. Claude Fable 5 and GPT-5.6 Sol held against every attack we ran, with no universal jailbreak found; we estimate they would likely cost more than $14,200 to jailbreak, if it is possible with this methodology at all. Meanwhile, we found hundreds of universal jailbreaks for Grok 4.5 and Gemini 3.1 Pro; each broke for under $300, with universal jailbreaks in Grok's weakest domain, cybersecurity, accessible for as little as $24. The gap is fixable: every weakness we found belongs to a known class of attack that already has a defense deployed in production models. The leaderboard will be updated on a rolling basis as new models are released, and the evaluation methodology and Minimal Standard will be periodically revised to take into account the latest capabilities and the state-of-the-art in safeguards. The leaderboard is available at leaderboard.far.ai.

Provenance-based intrusion detection systems (PIDS) frequently report strong performance, but the conclusions drawn from these results can be highly sensitive to benchmarking choices and evaluation protocols. We investigate this dependency by re-evaluating representative PIDS on public datasets that meet our audit, labeling, and calibration requirements. Focusing primarily on the audited DARPA TC E3 datasets, we apply a unified protocol with temporally separated test periods and validation-only checkpoint selection and threshold calibration, and ask which architectural claims are empirically supported. We find that alerting success and investigation utility can diverge sharply, as several systems surface attacks without providing enough process-level context to support forensic investigation. Across the four primary datasets, a simple allowlist built from executable names and paths observed during training matches or exceeds the selected learned baselines on key operating-point metrics, showing that comparable performance on these metrics is achievable using lexical novelty alone. Quantifying semantic signal quality through feature completeness and field entropy helps explain why several audited E3 datasets support alerting performance without reliably separating model architectures. In contrast, Theia provides the richest semantic signal and shows the clearest improvements in ranking and node-level recovery for our reference model. Overall, these findings reinforce the importance of interpreting architectural claims in PIDS together with the benchmark properties and evaluation protocol that produced them.

Cloud misconfiguration remains a leading cause of security incidents, yet whether LLMs and SLMs can generate security-compliant Infrastructure-as-Code is an open question. We benchmark seven models, three closed LLMs (Claude Opus 4, GPT-5.4, Gemini 2.5 Pro) and four open SLMs (Qwen2.5-Coder-14B, WizardCoder-33B, CodeLlama-13B, Magicoder-S-CL-7B), on AWS Terraform generation across 17 scenarios, integrating Checkov and Trivy scanners into a GitLab CI/CD pipeline and evaluating two prompt strategies at three security levels (pass@5). Syntactic validity and security compliance are largely orthogonal properties in LLM-generated IaC, a model that reliably produces well-formed Terraform does not necessarily produce secure Terraform: WizardCoder-33B achieves 77.8% validate rate yet zero Checkov compliance, while Claude Opus 4 reaches 23.1% Checkov and 92.5% Trivy pass rates under detailed security prompting. Consequently, prompt engineering alone is insufficient: automated multi-tool scanning remains a necessary complement to LLM-assisted IaC generation regardless of model family or prompt strategy. All artifacts are publicly available.

Coding agents increasingly run inside organizations whose security controls (scoped credentials, restricted egress, read-only filesystems, non-root execution) constrain them like any other software. Existing benchmarks, however, evaluate agents almost exclusively in permissive sandboxes, so it is unknown how performance changes when policy is enforced. In this work, we evaluate 12 coding agents on Terminal-Bench 2.1 across nested security policy levels derived from common real-world enterprise restrictions. Hardening is never free but far from uniform: under the strictest policy, success losses reach 18.3 points and cost inflation 167.3%, and the two axes disagree; the model that best preserves success is also the one that loses the most efficiency, so model choice is policy-dependent. Beyond aggregate scores, we characterize how agents behave when policy blocks their actions and decompose the failures hardening induces: runs grind into timeouts or wrong solutions rather than stopping early, in a mix that differs by model. To ground comparisons, we verify task solvability under the strictest policy, separating model failures from tasks the policy forecloses. We release Boundary-Bench, an open-source hardening plugin enabling policy-constrained evaluation of coding agents on Terminal-Bench and compatible benchmarks.

The Model Context Protocol (MCP) has seen rapid adoption since its November 2024 launch, with over 21,000 server instances detectable on the public internet. We present the first dynamic behavioral security assessment of internet-facing MCP servers, combining passive discovery across eleven data sources (crt.sh, HuggingFace, GitHub, npm, Smithery, PyPI, Censys, FOFA, Shodan, glama.ai, and pulsemcp.com) with active dynamic testing using Corvus, a purpose-built framework implementing 34 test modules covering 10 MCP-specific vulnerability classes. Across four measurement runs spanning July 2026, we confirm 640 production MCP servers and dynamically audit 414, uncovering 68 reportable vulnerabilities including SQL injection, SSRF targeting cloud metadata services, prompt template injection, and path traversal via cursor manipulation. We find that 91.8% of dynamically audited servers lack OAuth authentication, 687 tool instances across confirmed servers expose shell execution capabilities without access controls, and 41.6% of confirmed servers disappear within three days between consecutive measurement runs---indicating rapid deployment cycles without security review. We report on our responsible disclosure pipeline and release Corvus as an open-source framework for MCP security evaluation.

Agent-safety benchmarks measure different behaviors, and their scores get quoted interchangeably as an agent's safety. We treat four of them (R-Judge, InjecAgent, AgentHarm, AgentDojo) as measurements to be validated, running each under its official implementation and author-provided scorer on up to 22 models, with MMLU and GPQA measured by us under one protocol as a capability composite. The metric is the first problem. On any binary trace-judgment benchmark scored by $F_1$, an ``always positive'' policy attains $F_1 = 2π/(1+π)$; on R-Judge that is $0.690$, above five of the 21 models that actually discriminate. The three broad-coverage benchmarks then rank the same 18 models differently, and the trade-off behind that disagreement is a small-panel artifact: R-Judge specificity against AgentHarm safety correlates $-0.64$ at $n{=}7$ and $+0.02$ at $n{=}18$, and a quarter of random size-7 subsets reach $|ρ| \geq 0.5$ around that near-zero value. Held-out validity turns on which outcome you pick. Capability predicts task success ($ρ{=}{+}0.60$) but correlates negatively with misalignment safety ($ρ{=}{-}0.44$, $n{=}21$). On their paired $n{=}20$ panel, the corresponding contrast is $Δ{=}{-}1.00$ (95% CI $[-1.48, -0.49]$, $p<0.001$), and it survives leave-one-organization-out and organization-clustered bootstrap analyses. On an expanded 41-model panel, the misalignment correlation weakens to $-0.16$ (95% CI $[-0.54, +0.22]$) and jailbreak strengthens to $+0.34$, though neither change is significant. \mbox{AgentHarm} shows the strongest held-out association, $ρ{=}{+}0.72$ with three-template jailbreak safety after controlling capability. But both instruments score harmful compliance, so this is evidence of convergent validity rather than general safety. Naming the benchmark, metric, target behavior, and model panel is the minimum a safety claim needs.

Large Language Model (LLM) agents are increasingly adopted in real-world security operations with access to host artifacts and command-line interfaces (CLIs), making it critical to thoroughly assess their security capabilities. However, existing cybersecurity benchmarks focus on pre-compromise settings where agents are placed in a clean and idealized environment before an attack occurs. This leaves the post-compromise setting underexplored. To address this gap, we introduce SecRespond, the first benchmark for evaluating LLM agents on the post-compromise incident-response workflow. Given a forensic disk snapshot of a compromised host together with the alerts, vulnerability scans, and baseline checks reported by a host security product, agents are required to produce forensic reports on intrusions, baseline risks, and vulnerability risks, together with a remediation plan. We instantiate this task across 10 cyber ranges, each constructed from a distinct compromised cloud host, spanning 4 entry-point types, 21 ATT&CK techniques, and 5 operating systems. We evaluate 23 frontier LLMs on the OpenCode agent harness. Experimental results show that although current agents can reliably uncover the problems exposed by alerts, they struggle to proactively investigate the disk for silent intrusions and to produce comprehensive, verified remediation plans, with no model achieving complete detection and remediation on any single range. This reveals a fundamental bottleneck in building agents for real-world incident response. The benchmark is publicly available at https://github.com/Alibaba-NLP/qqr/tree/main/data/secrespond.

Stealth, the discipline of achieving an objective without revealing your presence, capabilities, or collected intelligence, is what separates sophisticated operators from detectable ones. Elite security researchers and advanced persistent threats achieve their objectives unnoticed; autonomous agents increasingly inherit the same offensive tasks, but do they inherit the tradecraft? We introduce StealthBench,a benchmark that measures operational stealth in autonomous offensive-security agents across six operational security (OPSEC) dimensions. We extract 11 hand-verified OPSEC incidents from real bug-bounty and red-team trajectories, expanded into 14 dockerized task scenarios, where agents, despite finding real vulnerabilities, committed stealth failures inconsistent with standard operational tradecraft: embedding credentials in public uploads, deleting production resources to prove access, force-adding uninvolved users to demonstrate a race condition. We evaluate agent trajectories using a 3-model large language model (LLM) judge panel with majority-vote aggregation, measuring safe success rate (solved and stealthy), Stealth@Solve (tradecraft quality among successful solves), and reckless solve rate (solved but cover blown). Our results show that no model exceeds 54% safe success rate (the compound metric requiring both task completion and stealth), confirming that OPSEC failures are systematic across model families. We release StealthBench as a public benchmark to support both the development of stealth-aware agents and automated OPSEC monitoring for autonomous offensive-security deployments. The interactive leaderboard, evaluation harness, and dataset are available at https://stealthbench.com.

Due to the lack of systematic evaluations, we are not yet able to determine which AI-based Windows malware detector to deploy in production, since existing evaluations (i) differ in terms of data used for both training and testing; (ii) do not consider temporal analysis to showcase whether models withstand the passage of time; (iii) avoid security evaluations with adversarial attacks that could highlight their brittleness against content-injection attacks; and (iv) neglect the computational requirements for deployment, risking slow inference on endpoints. For these reasons, we develop EXE-Bench, a comprehensive benchmark of AI-based Windows malware detectors. EXE-Bench assesses performance, temporal and adversarial robustness, and computational overhead, aggregating them into a single score for direct and fair model comparison. Through EXE-Bench, we highlight how evaluations conducted only after deployment are suboptimal and unable to provide a complete picture of their performance. In particular, through our analysis, we remark how much domain knowledge instilled through feature engineering is still extremely useful in this domain, resisting both time and adversarial attacks, in stark contrast with most of the deep networks that only excel right after deployment.

Large language model (LLM) agents routinely cheat on cybersecurity benchmarks, inflating reported pass rates far beyond genuine capability. Prior audits of Cybench found cheating in 0.3-3.4% of traces, implicating only a handful of models. We present a controlled prompt-ablation study across 22 frontier models from 7 providers on 23 Cybench capture-the-flag (CTF) challenges under three prompt conditions (no anti-cheat, standard, severe). All 1,518 task traces were individually audited through a four-stage pipeline combining LLM-as-a-judge classification, programmatic verification, judge-verifier reconciliation, and human review. We find cheating is far more pervasive than previously estimated: under baseline conditions, 37.1% of passes involved cheating, 21 of 22 models cheated, and scores were inflated by up to 5x. Anti-cheat prompts reduce cheat propensity from 33.0% (baseline) to 17.8% (standard) to 8.5% (severe) without degrading, and sometimes improving, solve rates. However, even under the most restrictive prompt condition, eight models still produced cheated passes, four showed backfire effects, and cheating escalated from web search toward infrastructure probing. We introduce the "solve rate" metric (clean passes only) to distinguish genuine capability from cheated outcomes, and argue it should be standard practice in any evaluation where cheating vectors are available. Anti-cheat prompts are an effective and essentially free first layer of defense, but they are not a substitute for environmental controls.

Security protocols verification relies on formal tools such as ProVerif and OFMC. This study evaluates whether large language models (LLMs) can perform comparable analysis. We test GPT and DeepSeek in chat and reasoning modes over three runs on 130 obfuscated AnB/AnBx protocols covering 388 security goals, scored against ProVerif and OFMC. Each provider uses a single model in both modes, switching reasoning on and off, so both contrasts isolate reasoning itself. Chat models achieve 72.7% recall at 27.3% precision for GPT and 69.3% recall at 27.2% precision for DeepSeek. Reasoning models reverse this trade-off, reaching 66.5% precision and 54.5% recall for GPT and 45.4% precision and 57.3% recall for DeepSeek. Enabling reasoning lifts precision from 27.3% to 64.8% for GPT and from 27.2% to 44.4% for DeepSeek on the consolidated verdict. The goal set is imbalanced, with 89 vulnerable goals against 299 secure ones; a trivial always-secure predictor scores 77.1% accuracy, which only GPT reasoning exceeds. All models perform worst on authentication goals: reasoning models detect well under half of injective and non-injective agreement attacks, whereas chat models over-flag them at low precision. Confidentiality is the exception, with F1 up to 95.7% in reasoning mode. Verdicts are unstable across runs: identical on 89.7% of goals for GPT reasoning, 74.0% for DeepSeek reasoning, 70.1% for GPT chat, and 61.6% for DeepSeek chat. Self-reported confidence is uniformly high yet shows no meaningful correlation with correctness. All results rest on a single zero-shot prompt and two model providers, which limits generalisability. On this benchmark, LLMs do not match formal verification, but may serve, at best, as pre-screening filters.

Malware analysis demands rapid interpretation of complex detonation reports spanning filesystem, network, and process behaviours. While large language models (LLMs) demonstrate impressive capabilities for technical artifact interpretation, the opacity and escalating API costs of closed-weight frontier models motivate exploration of open-weight alternatives. However, many open-weight models are large, demanding significant compute resources and incurring non-trivial hosting costs that place them beyond reach for resource-constrained deployments. This paper investigates whether orchestrated ensembles of small language models (SLMs) can match or exceed single LLM performance on structured questions about malware detonation reports. We established baselines by testing eleven open-weight SLMs, three cyber security pre-trained models, and six frontier LLMs on Meta's CyberSecEval Malware Analysis benchmark. We then designed and evaluated four orchestration architectures: (i) a multi-agent pipeline that decomposes analysis into structured evidence-collection and reasoning stages, (ii) an adversarial debate framework in which two agents iteratively critique each other's reasoning, (iii) a hierarchical consultation system that pairs a general-purpose SLM with a cyber-specialised expert model, and (iv) a hybrid architecture that combines evidence-grounded pipelines with adversarial debate reasoning. The hybrid system (Qwen3-4B with Foundation-Sec-8B) achieved 35.30% overall accuracy, exceeding the strongest cyber-specialised baseline (22.54%) and the strongest ungrounded frontier baseline (34.77%); when given the same evidence pipeline, grounded Gemini remained the strongest configuration at 38.22%. These findings show that evidence-grounded orchestration can substantially improve the performance of collaborative SLMs for supporting interpretation of malware detonation reports.

Traditional pentesting uses reconnaissance at each step to uncover unseen weaknesses, build stronger attacks, and advance the objective; we argue that AI agents require the same treatment. We formalize agent reconnaissance by modeling the process and identifying the knowledge assets it seeks to extract: what they are, how they are used, and which agent weaknesses they exploit to give adversaries leverage in indirect prompt injection attacks. We instantiate these insights in Know Your Agent (KYA), a framework that automates black-box, reconnaissance-driven pentesting by probing agents, building target profiles, and using those profiles to craft stronger attacks. We evaluate KYA on agent-security benchmarks and a real-world coding agent, and release KYA, its benchmarks, and baseline implementations for reproducibility.

Large language models (LLMs) are increasingly used for a range of software, hardware and human-centered security tasks. Consequently, LLM performance on security tasks is an active area of measurement and research, often with a focus on identifying areas in which LLM security "knowledge" may be insufficient. Popular strategies for identifying LLM security knowledge gaps include building corpora of challenge questions or task benchmarks, strategies that require substantial manual work and security expertise to design and execute. We introduce a partially-automated method for assessing LLM knowledge of a security area. The method uses authoritative information from Consumer Protection Agencies (CPAs) to identify instability in LLM responses that can be indicative of knowledge gaps. We demonstrate the method for 2 security topics, identity theft and impostor scams, and 5 LLMs in 2 leading LLM families, Gemini and GPT, using publicly available information about identity theft and impostor scams from 6 CPAs. The method distinguishes between models that have and don't have sufficient knowledge to accurately identify the security topics in text narratives.

Large language model (LLM) agents are starting to take on routine work in high-performance computing (HPC), including monitoring Slurm jobs, diagnosing failed builds, inspecting simulation output, and coordinating scientific workflows. To do this work, an agent commonly acts under its user's credentials and inherits the user's access to files and the scheduler. This arrangement creates a failure mode that ordinary account-level controls do not capture. Adversarial instructions in a log, tool description, shared file, or peer-agent message may redirect the agent beyond the task the user assigned, even though every resulting command is authenticated and permitted for that account. We refer to this as the hijacked authorized agent problem. Existing agent-security studies explain relevant mechanisms, such as indirect prompt injection and tool misuse, but generally evaluate them in web, enterprise, or personal-assistant settings. HPC security, by contrast, has mature controls for identity and isolation but does not ordinarily represent the intent of a particular task. This paper defines the threat model in the HPC setting, identifies attack surfaces created by schedulers, shared storage, multi-project accounts, and scientific workflows, and examines where current controls fall short. It concludes with a research agenda and a plan for an empirical benchmark, TaskBound.

Data-driven pre-fault dynamic security assessment (DSA) rapidly evaluates the dynamic risk of credible contingencies on a power system using machine learning. Existing approaches face two limitations. First, they require a large labelled database for training, with a separate model trained, tuned, and maintained for each contingency in a potentially long list of credible contingencies. Second, the trained models generalize poorly to unseen contingencies. This work addresses the limitations by using a tabular foundation model (TFM) that assesses stability through in-context learning, requiring no retraining or hyperparameter optimization. A single TFM can assess many contingencies at once, removing the need for one model per classifier. We also characterize when the use of electrical distance coordinates (EDC) as continuous features enables generalization of TFM to unseen contingencies and when they do not, demonstrating how a few labelled samples can reliably improve generalization. Through comprehensive case studies on the IEEE 68-bus system, we show that a single TFM attains an average Macro F1 score of about 90% with only 120 labelled samples per contingency, roughly two orders of magnitude fewer than conventionally assumed, without any model retraining or hyperparameter tuning. For new/unseen contingencies, we show that using just 10 labelled samples of the new contingency with EDC encoding matches the best achievable transfer learning oracle model, which requires fully labelled data and is not deployable in practice. Overall, this initial study paves the way towards developing and deploying foundation models for power system operations, with possible applications across multiple operational tasks.

Security rating platforms summarize externally observable cyber exposure and are expected to help organizations prioritize remediation. A platform may want to tell an organization how a candidate remediation action would affect its score, but repeatedly exposing exact score responses can reveal information about the hidden scoring engine. We propose a surrogate based approach for remediation score impact prediction that is designed to respect this opacity constraint. The surrogate predicts scores from organization configurations while explicitly representing checkpoint (i.e., a security check) applicability and the observed checkpoint set. A main challenge is that such predictions are not uniformly reliable: they depend on the amount and structure of the observable checkpoint evidence available for a given configuration. To address this, the approach combines applicability-aware surrogate construction, sensitivity analysis under controlled checkpoint restriction, a reliability layer for identifying unstable predictions, and score-impact prediction for supported remediation actions. Explicit modeling of checkpoint applicability is central throughout: it improves score prediction and provides the feature basis used by the reliability layer to identify unstable cases. We evaluate the approach on a real-world dataset of 5,188 organization configurations from a commercial security rating platform. The results show that the applicability-aware surrogate improves score prediction over simpler feature representations. For remediation, the surrogate predicts the score impact of supported actions, while the reliability layer helps identify cases in which these predicted impacts should be interpreted cautiously.

AI coding agents produce code faster than humans can review it. In our approach, the prover is the judge of whether the code is correct. Under a verifier-driven loop, AI agents wrote and verified bare-metal security software in Ada/SPARK spanning classical and post-quantum cryptography, TLS 1.3, IKEv2, X.509, and a Matrix client. GNATprove discharged 49,280 proof obligations, established functional correctness for selected primitives, and proved the absence of run-time errors for the rest, at roughly 20-40 times lower supervision cost than comparable hand verification. GNATprove alone was insufficient: some defects could not be detected and were resolved using known-answer tests, interoperability, or human review of specifications. Given weak checks, the agent tried to bypass them and reported success. We report where each layer caught faults and draw the central lesson: what an agent can be trusted to establish is bounded by the strength of its feedback.

Artificial Intelligence (AI), especially Generative AI (GenAI), adoption has increased in industries significantly in recent years. However, the use of these models may also expose systems to new forms of cyberattacks by different malicious actors -- adversarial prompt attack (APA) being one of the most prominent examples of such threats. This paper presents the implementation of an Adversarial Prompting Framework (APF) for a comprehensive assessment of AI safety. The framework systematically evaluates the resilience of the AI model through the generation of structured adversarial prompts at multiple sophistication levels, from direct harmful requests to advanced encoding-based attacks. Our implementation demonstrates the practical application of this methodology in enterprise environments, providing automated testing capabilities with quantitative security assessment metrics. The results indicate significant variations in the model vulnerabilities across different attack vectors, with encoded prompts presenting the highest success rates in bypassing safety mechanisms.

Clinical AI models can expose patients to harm when adversarial vulnerabilities go undetected, yet formal security auditing requires statistical expertise, specialized tools, and significant time. We present an open evaluation task, built on METR Task Standard v0.3.0, that tests whether frontier AI agents can autonomously implement a structured clinical AI security audit. Given a pre-trained clinical prediction model, a patient dataset, and written instructions, each agent must implement four attacks from pseudocode, compute a Security Posture Score covering FGSM robustness, membership inference resistance, expected calibration error, and boundary attack resistance, and write a structured JSON report in a Docker container using only a bash interface and no scaffolding code. Six variants span the Wisconsin Diagnostic Breast Cancer and MIMIC-IV ICU mortality datasets across three model architectures with increasing defense strength, with reference scores from 55.60 to 90.41. We ran 54 evaluations across three frontier models, with three runs per variant. Claude Sonnet 4.6 and GPT-4.1 completed all 18 runs and received perfect evaluator scores. GPT-4o completed 61 percent of runs and used about five times the per-run token count of Claude, although provider tokenization differs. Total API costs were 8 US dollars for GPT-4.1, 12 US dollars for Claude Sonnet 4.6, and 27 US dollars for GPT-4o. GPT-4o failures involved premature session termination, an aggregation error, and an empty submission file. The task, scoring infrastructure, and Wisconsin Breast Cancer assets are publicly released; MIMIC-IV variants require separate PhysioNet access.

Exposed documents such as emails, chat threads, tickets, and incident notes routinely leak credentials, but during incident response a leaked secret is only half the story. Responders also need to identify the ``door'' the secret opens: the account, tenant, endpoint, database, cloud resource, or other system that the credential could allow an attacker to access. Traditional secret scanners rely on regular expressions or trained classifiers which work well on well-formatted code, yet they struggle when a credential is fragmented, reformatted, or far from the resource it unlocks, and they report the secret string without naming what it opens. We present Secret Scanner Agent (SSA), a multi-agent large-language-model system that extracts both the secret and its associated door, together with supporting evidence, from unstructured exposed documents. SSA pairs a detection agent that favors recall with a review agent that filters false positives and recovers missing context. Because real credential data is sensitive, we evaluate SSA on synthetic benchmarks we generated that span 23 secret types and multiple document formats, scored with a three-step pipeline of programmatic matching, an LLM judge, and human review. Across six models, multi-agent SSA improves extraction precision over a single-agent variant, with the largest gains on door extraction, by up to 16 percentage points. SSA matches a regular-expression scanner's precision while more than tripling its recall, and against thirteen security analysts it is more precise, recovers nearly twice as many secret--door pairs, and runs five to seventeen times faster. By returning the secret, its door, and supporting evidence in one result, SSA turns credential detection into an actionable finding for triage and remediation.

i-EXAM is a planning-powered tool that helps system administrators to create security profiles of complex networks and perform what-if analyses to identify network hardening strategies. It leverages planning compilation that provides soundness and completeness guarantees to identify attack paths, evaluate security metrics, generate diverse hardening strategies, and explain these strategies in natural language using Large Language Models.

Large language model agents driving security tool suites over the Model Context Protocol are increasingly common. Yet the factors that bound their capability remain poorly characterized: how much depends on the model versus the client that drives it, whether constraining the agent to the orchestrator's own tools helps, and where capability is limited by reasoning rather than by missing tools. Using HexStrikeAI, an open-source orchestrator that exposes 150+ tools, as a testbed, we follow a methodology that evaluates the system, diagnoses its failures, and applies targeted improvements. We run 86 picoCTF challenges across seven categories and three difficulty tiers, under three tool-access regimes and three model/client configurations (774 trials). We then apply corrections to existing tools, agent-behavior changes, and eleven new capability tools, and re-run the previously-unsuccessful trials. The diagnosis isolates the driving client as a first-order factor for a fixed model (a 2.1 * gap between two DeepSeek clients) and a monotonic difficulty gradient, with the largest gains in the mid tier. The overall solve rate rises from 55.4% to 72.0%, and every configuration improves significantly (paired McNemar p < 0.001, non-overlapping 95% confidence intervals). The residual failures are reasoning- or environment-bound rather than missing-tool. A 60-run stability sub-study finds single-run verdicts reproducible (17/20 unanimous). We discuss what the results imply for how such orchestrators should be evaluated, and we are explicit about the limits: the study uses a single benchmark, the fixes were tuned on the same challenges they were evaluated on, and the client effect is demonstrated for one model only, so its generality to other models remains a hypothesis.

The rapid deployment of AI systems across high-stakes domains has created urgent demand for standardized evaluation, yet the field remains fragmented across competing risk taxonomies that catalog risks without showing how an audit is executed. At least 74 AI risk taxonomies exist, and almost all stop at the catalog. The hard part of auditing is not naming a risk but operationalizing it: turning it into a test run against a real system, a measured value, a calibrated severity, and a defensible grade. This paper leads with that bridge. We present the operationalization layer Eticas has built and run, shown end to end on a single risk (PII leakage) against a public benchmark, and then the open taxonomy that makes the method scale. On GPT-4-0314, a disclosure risk that seven external frameworks require be controlled is measured at 0%, 51%, and 84% disclosure as adversarial conditioning increases, mapping through calibrated severity bands to a subcategory grade of E with a SYSTEMIC pattern. Around this example, the Eticas AI Risk Taxonomy v2.0.0 organizes 76 active subcategories across 10 categories and 20 sub-groups, with mappings to 18 external frameworks across compliance, reference, and academic tiers. Its category and sub-group layer is published under CC BY 4.0 as open semantic infrastructure with stable URIs and SKOS/JSON-LD distributions, and a worked subcategory example shows the operational layer down to its severity thresholds. The contribution is the demonstrated bridge from concept to graded finding, anchored by a clean separation of risks from the mechanisms by which they surface, and framed by an open-core model in which the conceptual scaffold is open and the methodology calibration is the practitioner layer. This is the infrastructure the AI auditing field needs: shared, open, and demonstrably operable.

Claw-like AI agents (e.g., OpenClaw) are always-on processes with persistent access to credentials, files, tools, and external services. They take on system-level responsibilities -- installing packages, maintaining state, scheduling subtasks, and mediating I/O -- making security failures far more severe than in other agents. Yet existing benchmarks focus on model responses and tool calls, leaving cross-component failure modes largely unmeasured. We adopt a computer-system analogy: treating a Claw-like agent as an agentic computer system whose gateway runtime plays an OS-like mediation role, whose Skills resemble user-installed applications, and whose Plugins resemble loadable extensions with runtime privileges. Each component has a classical counterpart whose protection mechanisms -- refined over decades of cybersecurity research -- are absent on the agent side. From this perspective, we develop SafeClawArena, a benchmark of 406 adversarial tasks across four attack surfaces (Skill Supply-Chain Integrity, Persistent State Exploitation, Cross-Boundary Data Flow, and Indirect Prompt Injection), executed in containerized replicas of real agent platforms with canary-marked credentials and evaluated via automated taint tracking across nine output channels. We evaluate three platforms (OpenClaw, NemoClaw, SeClaw) and five frontier LLMs. The highest attack success rate reaches 70%; malicious Plugins succeed in 100% of cases regardless of the LLM. SeClaw cuts GPT-5.4's attack success rate from 70% to 22%, partly through utility-security tradeoffs rather than active defenses, while Claude-Opus-4.6 already sits near a 22% floor on every platform. These results expose the inadequacy of current defenses and suggest directions for future hardening. Code and data: https://github.com/sunblaze-ucb/SafeClawArena.

LLM evaluation and AI safety face a shared measurement problem: benchmark scores, reward-model signals, and reported safety metrics can improve while the latent properties they are meant to represent remain difficult to verify. This paper combines a hybrid survey - a systematic search paired with narrative synthesis and separately tracked grey evidence - with a conceptual framework and a structured ten-model audit. The synthesis spans eight evidence streams: benchmark validity, dynamic evaluation, LLM-as-judge reliability, safety evaluation, jailbreak/refusal robustness, reward hacking, mechanistic interpretability, and governance/auditability, covering 2018-2026 evaluation-safety measurement work. We introduce EvalSafetyGap as an organizing hypothesis for comparing evaluation-side and alignment-side proxy failures under optimization pressure, using Goodhart's Law together with two constructs we develop here - an Instability Decomposition and an Alignment Trilemma - as tools for generating testable comparisons. The audit shows how conclusions shift when capability, behavioral safety, and governance are measured separately. In this sample ($n = 10$), the association between capability and sustained adversarial robustness is statistically indeterminate using the displayed Table 3 inputs (Pearson $r = +0.232$, $p = 0.520$), and the apparent open-closed safety gap is modest, driven mainly by governance and disclosure rather than behavioral robustness, and sensitive to how a single borderline model is classified; attempt-budget results are protocol dependent. Because the public evidence uses heterogeneous protocols, the audit is diagnostic rather than rank-generating. The contribution is a shared vocabulary and evidence map to support dynamic evaluation, transparent source reporting, multi-attempt safety measurement, and auditable alignment practice.

Agent-based AI has enabled the automation of tasks by exposing application tools and resources to large language models (LLMs). However, to improve scope and accuracy, agents are often given access rights that exceed those of ordinary users, introducing significant security risks. AI is routinely integrated into applications with a disregard to security, risking data exposure and breaching regulations. This paper applies the AI Trust, Risk, and Security Management (TRiSM) framework to a medical report-generation application to demonstrate how an insecure agent workflow can be transformed into security-conscious agentic workflow. Both workflows were evaluated across five LLMs (Claude Haiku 4.5, GPT-4.1-nano, GPT-4.1-mini, GPT-5.4-mini, and Gemini 2.5 Flash) on two report types, totalling 800 generations and 500 attack scenarios including RAG poisoning, data-field injection, and client-side network injection. The TRiSM-guided agentic workflow reduced mean attack success rates from 31% to 10% for RAG poisoning and from 42% to 25% for data-field injection, while eliminating the network injection vector entirely through server-side prompt construction. Furthermore, report accuracy increased by 14 percentage points (72.5% to 86.5%) with the agentic workflow, demonstrating a secure design which provides more reliable outputs. This paper contributes to knowledge by demonstrating least-privilege, defence in depth agentic workflows improving security and accuracy, while also highlighting model choice is a necessary architectural consideration.

Tool-using language-model agents introduce security failures that go beyond unsafe text: they can disclose protected objects, write persistent memory, send messages, modify databases, or trigger harmful code and tool effects. Existing evaluations often collapse these stages into a single attack success rate, making it difficult to tell whether a model merely agreed with an attacker or actually produced observable harm. We introduce SafeClawBench, a staged benchmark for tool-using agent security with 600 controlled adversarial tasks across six attack families: direct and indirect prompt injection, tool-return injection, memory poisoning, memory extraction, and ambiguity-driven unsafe inference. SafeClawBench reports three separate endpoints: semantic attack acceptance, audit-visible harm evidence, and sandbox-observed tool/state harm. Evaluating five agent endpoints under four prompt-level policies, we find that these endpoints capture different failure modes. Without additional prompt protection, semantic failure rates vary widely across models, from 9.0% to 44.2%. Audited harm evidence is narrower than semantic failure, and under a separate executable protocol some matched task identities produce sandbox harm despite passing the Semantic Core call: in a 12,000-row matched analysis, 291 of 347 observed sandbox harms occur in rows that pass the semantic check. Prompt policies change endpoint outcomes, but their effects depend on both model and protocol. SafeClawBench provides a reproducible framework for comparing agent models and prompt-policy conditions without conflating textual compliance, evidence-supported harm, and executable state changes. The open-source dataset is available at https://huggingface.co/datasets/sairights/safeclawbench.

A protocol driven framework is presented that binds SBOM and AIBOM artefacts to deterministic environment capture and structured runtime telemetry. Exploitability is computed from declared artefacts, observed activation conditions, and enforced execution policies. CSAF VEX advisories are generated from combined static and runtime evidence, cryptographically signed, and validated through deterministic replay. Evaluation uses approximately 10000 component entries across synthetic Agentic AI workloads 50 to 5000 components, incorporating OSV, GitHub Advisory, KEV, and EPSS datasets.

Compared with binaries and decompiled code, malware source code more directly reflects the attackers' original intent. However, the scarcity of source code and the high cost of manual review make such datasets difficult to build and maintain. We propose MASCOT-Android, a curated dataset of Android malware source code and an automated collection framework for scalable malware source code discovery on GitHub. A key finding of our work is that repository-level documentation alone provides a strong signal for malware source code collection. Our model extracts character-level TF-IDF features from 8,772 malware and 25,747 benign README documents and trains a LinearSVC classifier to distinguish malware repositories. This README-only model achieves an accuracy of 96.28% and an FPR of 1.06% in local evaluation. In addition, the model outputs confidence scores, allowing users to adjust the decision threshold to balance FPR and coverage, which is practical in real-world malware source code collection.

Open-source LLM agent ecosystems are growing rapidly, yet the security of community-contributed skills - modular tool definitions that extend agent capabilities - remains largely unvetted. The gap we fill: existing scanners operate at the code layer and are structurally blind to instruction-layer and multi-agent risk - natural-language directives that hijack an agent, exfiltrate data through encoded side channels, or chain harm across pipelines - so what is needed is a semantic, multi-dimensional vetting system rather than another signature matcher. We present SKILLVETBENCH, a live public leaderboard on Hugging Face that uses an LLM-as-Judge to vet agent skills. What is new: SARS (Skill Agentic Risk Score), a five-dimensional agentic-risk metric with a principled weighted formula for instruction-following systems. What is integrated: full CVSS v4.0 vector decomposition and a ClawHub dual-view that places our LLM-generated review beside the official marketplace verdict. What is demonstrated: drawing on our companion benchmark paper [ 1], the LLM-as-Judge stage achieves zero false negatives across 78 confirmed-malicious skills and zero false positives across 22 benign controls, while the best static baseline (SKILLSIEVE) still misses 15%; for instruction-layer categories such as Prompt Injection and Memory Poisoning, conventional tools miss between 89% and 100% of threats (e.g., CODEBERT detects none of nine memory-poisoning skills). Detection rates vary from 35% to 95% across four LLM evaluators, motivating ensemble scoring in production deployments.

This paper presents a structured analysis of security challenges in long-horizon agentic AI systems. The study reviews existing threats, evaluation approaches, attack propagation mechanisms, and security frameworks. A taxonomy of security threats and a framework for analyzing attack propagation are proposed to support future research in agentic AI security

This paper explores the value of agentic AI tools for cybersecurity purposes. We evaluate the efficacy of a general-purpose GenAI Large Language Model- (GenAI-) based agent when powered by three different Ollama-hosted general-purpose open source models. We assess each agent's performance using precision, recall, false positive count, and a calculated composite score based upon the interplay of the captured metrics, against the baseline performance of an existing, vetted Static Application Security Testing (SAST) tool, Bandit. Our findings refute the notion that a modern open-source GenAI LLM-based agent is currently suitable for the specialized task of SAST scanning under realistic conditions.

Large language models (LLMs) are rapidly acquiring capabilities relevant to biological research, from literature synthesis to interpretation of experimental data. Increasingly, LLM agents can also perform in silico biology tasks that previously required experienced human biologists. These emerging AI capabilities offer new opportunities for scientific discovery and biomedical advances, but they also shift the landscape of biosecurity risks. To address this, we introduce the Agentic Bio-Capabilities Benchmark (ABC-Bench), a suite of tasks to measure agentic biosecurity-relevant capabilities. ABC-Bench evaluates LLM agents on both benign and dual-use biology tasks: writing code to operate liquid handling robots, designing DNA fragments for in vitro assembly, and evading DNA synthesis screening. These tasks require a combination of biology and software expertise. All tested LLM agents outperformed the median expert human baseliner on all three tasks. Agents performed highly on tasks drawing on published knowledge and well-documented protocols, and more weakly on a task requiring novel bioinformatics reasoning. In three wet-lab validation experiments, we found that OpenAI's o4-mini-high produced scripts that, when run on an OpenTrons liquid handling robot, successfully assembled DNA with expected sequences.

This paper presents AuditBench, a new benchmark dataset for evaluating the capabilities of LLMs at investigating security-related system audit logs. We design and use this benchmark to explore the performance of LLMs on four log-investigation tasks that incident response teams commonly perform, ranging from triaging alerts generated by detectors to identifying persistence mechanisms on compromised systems. AuditBench consists of system audit logs collected from Linux and Windows machines, and spans over 50 different security investigation scenarios, including both malicious and benign activity. Using our benchmark, we evaluate and analyze the performance of five frontier LLMs at analyzing audit logs for attack investigations. Our analysis illuminates how LLM performance and error profiles vary according to different design choices, such as differences in model size, data representation, prompt construction, and specific investigation tasks. Additionally, we characterize the quality of the explanations produced by LLMs and the types of errors that models make across our benchmark. Collectively, our work provides a foundation for assessing the capabilities of LLMs for investigating security logs, novel insights for practitioners using LLMs in security operations, and important directions for future research.

AI has the potential to transform cybersecurity by enabling systems that can autonomously detect, analyze, and remediate software vulnerabilities. However, existing cybersecurity evaluations of AI systems are limited in scale or scope, and fail to capture the end-to-end lifecycle of real-world software vulnerability discovery and remediation. To address this gap, we propose CyberGym-E2E, a large-scale and realistic end-to-end cybersecurity benchmark that comprehensively evaluates AI agents' abilities across the full lifecycle of vulnerability discovery, PoC generation, and patch generation. CyberGym-E2E is comprehensive and scalable, as we build an automated, agent-enhanced pipeline for transforming open-source vulnerability data into realistic evaluation environments. Currently, the benchmark consists of 920 real-world vulnerabilities across 139 different open-source projects.

Published evaluations of prompt-injection and jailbreak detectors for Large Language Models often suffer from two systematic weaknesses: per-dataset threshold tuning and undisclosed operating points. We describe an evaluation harness that addresses both. The detector under evaluation is scored across 16 public benchmarks (12,111 samples) using 5-fold cross-validation. StratifiedKFold (by row) is the headline pass; a parallel StratifiedGroupKFold pass over a composite key (parent-prompt id plus MinHash + LSH near-duplicate clusters at Jaccard $\gtrsim 0.8$) runs alongside it as a leakage-premium diagnostic. A single global operating point is selected on the held-out folds (max F1 subject to FPR $\leq 1\%$) and applied uniformly to every dataset, so per-dataset results reflect one threshold rather than per-benchmark optimisation. Generalisation is examined through a battery of diagnostics (leave-one-dataset-out cross-validation, a random-label control, adversarial validation, permutation feature importance, length-bias correlation, classifier-head agreement, cross-source near-duplicate detection, threshold transferability, train-vs-OOF agreement, and a paraphrase-invariance probe), most with a quantitative pass threshold and the remainder with a stated failure mode. For every external comparison, the detector's threshold is re-tuned to the competitor's published false-positive rate so head-to-head values are evaluated at matched operating points.

Autonomous LLM agents increasingly operate in stateful environments where they access tools, files, memory, and external services. While such capabilities enable complex real-world workflows, they also introduce security risks that are difficult to capture with existing evaluations. Current agent security benchmarks often rely on manually curated tasks, provide limited coverage of emerging threats, and focus primarily on final outcomes rather than the execution processes that lead to unsafe behavior. We introduce SeClaw, a framework that combines specification-driven security task synthesis with execution-based security evaluation for Autonomous agents. Spec-driven security task synthesis enables scalable and controllable construction of security tasks from structured risk specifications, while SeClaw docker provides a standardized testbed for evaluating agent behavior under diverse safety-risk scenarios. The benchmark covers risks arising from resources, user tasks, environments, and intrinsic agent behaviors, and supports trajectory-aware assessment of unsafe actions beyond final responses. By bridging systematic task synthesis and reproducible security evaluation, SeClaw provides a practical foundation for measuring, diagnosing, and comparing security failures in autonomous LLM agents. The code is available at https://github.com/seclaw-eval/seclaw-eval.

We analyzed 3,984 AI agent skills from major marketplaces and found 76 confirmed malicious payloads, including credential theft, backdoor installation, and data exfiltration. 13.4% of all skills contain at least one critical-level security issue and at least 8 manually confirmed malicious skills remain publicly available on clawhub.ai as of the date of publication. This report documents our methodology, presents a threat taxonomy based on real-world samples, and details the attack patterns we observed. As skill marketplaces grow rapidly and AI agents gain access to sensitive credentials and systems, automated security analysis is no longer optional.

The Model Context Protocol (MCP) standardizes how a large-language-model (LLM) agent and an external tool server exchange messages, but not trust: a host reads a server's self-declared tool list and dispatches calls, with no notion of which servers it may use, at what sensitivity, or which of a server's tools are in bounds. This work grew out of a concrete need -- letting the Enclawed agent use Google's externally-operated MCP servers (Gmail, Calendar, Drive) safely, admitting the server and bounding the tools it may drive, without changing MCP or Enclawed's own tool application-programming interface (API). The mechanism we built, mcp-attested (shipped in both the open enclawed-oss distribution and the enclaved flavor), generalizes: the gap that makes an unmediated third-party connection unsafe for one user makes a regulated deployment impossible to accredit. We close it with three additive mechanisms: (1) a small, offline-signed clearance assertion a server publishes at a well-known Uniform Resource Identifier (URI) and a host verifies against a pinned trust root before any tool dispatch; (2) a deny-by-default per-server tool allowlist, so admitting a server is not trusting its every tool; and (3) a flavor-gated enforcement mode that turns the checks from warnings into hard denials, with every decision written to a tamper-evident audit log. We give the wire format, the verification algorithm, a security analysis, and an LLM-driven adversarial evaluation; we then state the design in normative Request-for-Comments (RFC 2119) form -- schema, verification rules, error registry, well-known registration, and machine-checkable conformance vectors -- so it can be adopted as an MCP addendum rather than reinvented. An unextended host ignores the well-known document and behaves exactly as today.

Tools like Tamarin and ProVerif have achieved notable success in analyzing and verifying complex real-world protocols such as EMV, 5G, and WPA2, even detecting zero-day exploits. Despite these successes, verifying such protocols remains a time-consuming, challenging task, often requiring significant human effort and expertise. In this paper, we present a reinforcement learning (RL) framework inspired by AlphaZero and AlphaProof that implements a new style of proof search for Tamarin. We have developed a stateless API for Tamarin that acts as a classical RL environment. We guide a Monte Carlo Tree Search (MCTS) by a neural heuristic that learns from completed subproofs. We evaluate our framework on 16 case studies, ranging from classical protocol models to challenging state-of-the-art protocol models from recent publications. Our method finds more proofs automatically than Tamarin's standard search and produces shorter proofs than both the standard and human-engineered heuristics. Our pipeline is applicable out of the box to assist Tamarin users in active research, reducing the human effort required. Moreover, our standardized interface provides a programmatic way for users to interact with Tamarin. Finally, our work demonstrates the promising potential of adapting RL-based methods to the Tamarin domain.

This work examines an imbalance in artificial intelligence (AI) security research: the field tends to produce more work on attacking AI systems than on defending them. Drawing on related academic papers, we find biased attack-to-defense ratios across subfields, including federated learning, speech recognition, membership inference, large language models, etc. The imbalance possibly means far beyond a simple count: attack papers are routinely evaluated under favorable conditions that make threats look more severe than they are in practice, while defenses are held to a stricter standard that few can meet. The result is a literature rich in demonstrated vulnerabilities and thin on usable and deployed protections. We thus argue that AI security research should better incentivize defense research.

The benchmarks used to evaluate AI agents in security-critical roles suffer from crucial weaknesses. Building on recent empirical evidence, we characterize three core challenges that undermine security evaluations: benchmark vulnerabilities, temporal staleness, and runtime uncertainty. We then outline practical directions toward building more robust and trustworthy evaluation frameworks.