LLM Agent Security

Large Language Model (LLM)-based Multi-Agent Systems (MASs) are increasingly deployed for agentic tasks, such as web automation, itinerary planning, and collaborative problem solving. Yet, their interactive nature introduces new security risks: malicious or compromised agents can exploit communication channels to propagate misinformation and manipulate collective outcomes. In this paper, we study how such manipulation can arise and spread by borrowing the Friedkin-Johnsen opinion formation model from social sciences to propose a general theoretical framework to study LLM-MAS. Remarkably, this model closely captures LLM-MAS behavior, as we verify in extensive experiments across different network topologies and attack and defense scenarios. Theoretically and empirically, we find that a single highly stubborn and persuasive agent can take over MAS dynamics, underscoring the systems' high susceptibility to attacks by triggering a persuasion cascade that reshapes collective opinion. Our theoretical analysis reveals three mechanisms to increase system security: a) increasing the number of benign agents, b) increasing the innate stubbornness or peer-resistance of agents, or c) reducing trust in potential adversaries. Because scaling is computationally expensive and high stubbornness degrades the network's ability to reach consensus, we propose a new mechanism to mitigate threats by a trust-adaptive defense that dynamically adjusts inter-agent trust to limit adversarial influence while maintaining cooperative performance. Extensive experiments confirm that this mechanism effectively defends against manipulation.

Autonomous LLM-based agents increasingly operate as long-running processes forming densely interconnected multi-agent ecosystems, whose security properties remain largely unexplored. Systems such as OpenClaw, an open-source platform with over 40{,}000 active instances, persistent configurations, tool-execution privileges, and cross-platform messaging, are deployed at scale, yet the security of such agent ecosystems remains largely unexplored. This work presents AgentWorm, the first self-replicating worm attack against a production-scale agent framework, achieving a fully autonomous infection cycle initiated by a single message: the worm first hijacks the victim's core configuration to establish persistent presence across session restarts, then executes an arbitrary payload upon each reboot, and finally propagates itself to every newly encountered peer without further attacker intervention. The attack is evaluated on a controlled testbed across five distinct LLM backends, three infection vectors, and three payload types. Results show a 63% aggregate attack success rate, sustained multi-hop propagation, and stark divergences in model security postures, highlighting that while execution-level filtering effectively mitigates dormant payloads, skill supply chains remain universally vulnerable. Defenses are evaluated at three layers (prompt-level mitigations sourced from real community practice, the framework's built-in security controls, and an ecosystem-wide measurement of public configurations), revealing that the critical controls capable of breaking the infection loop are not enabled in any of the observed deployments. A cross-framework transferability experiment on Hermes Agent confirms that the underlying vulnerabilities are properties of the autonomous agent design pattern, not artifacts of a single implementation.

Large Language Model (LLM) agents increasingly use external tools for complex tasks and rely on embedding-based retrieval to select a small top-k subset for reasoning. As these systems scale, the robustness of this retrieval stage is underexplored, even though prior work has examined attacks on tool selection. This paper introduces ToolFlood, a retrieval-layer attack on tool-augmented LLM agents. Rather than altering which tool is chosen after retrieval, ToolFlood overwhelms retrieval itself by injecting a few attacker-controlled tools whose metadata is carefully placed by exploiting the geometry of embedding space. These tools semantically span many user queries, dominate the top-k results, and push all benign tools out of the agent's context. ToolFlood uses a two-phase adversarial tool generation strategy. It first samples subsets of target queries and uses an LLM to iteratively generate diverse tool names and descriptions. It then runs an iterative greedy selection that chooses tools maximizing coverage of remaining queries in embedding space under a cosine-distance threshold, stopping when all queries are covered or a budget is reached. We provide theoretical analysis of retrieval saturation and show on standard benchmarks that ToolFlood achieves up to a 95% attack success rate with a low injection rate (1% in ToolBench). The code will be made publicly available at the following link: https://github.com/as1-prog/ToolFlood

While large language model-based agents demonstrate great potential in collaborative tasks, their interactivity also introduces security vulnerabilities. In this paper, we propose and model group collusive attacks, a highly destructive threat in which multiple agents coordinate via sociological strategies to mislead the system. To address this challenge, we introduce GroupGuard, a training-free defense framework that employs a multi-layered defense strategy, including continuous graph-based monitoring, active honeypot inducement, and structural pruning, to identify and isolate collusive agents. Experimental results across five datasets and four topologies demonstrate that group collusive attacks increase the attack success rate by up to 15% compared to individual attacks. GroupGuard consistently achieves high detection accuracy (up to 88%) and effectively restores collaborative performance, providing a robust solution for securing multi-agent systems.

This article, a lightly adapted version of Perplexity's response to NIST/CAISI Request for Information 2025-0035, details our observations and recommendations concerning the security of frontier AI agents. These insights are informed by Perplexity's experience operating general-purpose agentic systems used by millions of users and thousands of enterprises in both controlled and open-world environments. Agent architectures change core assumptions around code-data separation, authority boundaries, and execution predictability, creating new confidentiality, integrity, and availability failure modes. We map principal attack surfaces across tools, connectors, hosting boundaries, and multi-agent coordination, with particular emphasis on indirect prompt injection, confused-deputy behavior, and cascading failures in long-running workflows. We then assess current defenses as a layered stack: input-level and model-level mitigations, sandboxed execution, and deterministic policy enforcement for high-consequence actions. Finally, we identify standards and research gaps, including adaptive security benchmarks, policy models for delegation and privilege control, and guidance for secure multi-agent system design aligned with NIST risk management principles.

High-privilege LLM agents that autonomously process external documentation are increasingly trusted to automate tasks by reading and executing project instructions, yet they are granted terminal access, filesystem control, and outbound network connectivity with minimal security oversight. We identify and systematically measure a fundamental vulnerability in this trust model, which we term the Trusted Executor Dilemma: agents execute documentation-embedded instructions, including adversarial ones, at high rates because they cannot distinguish malicious directives from legitimate setup guidance. This vulnerability is a structural consequence of the instruction-following design paradigm, not an implementation bug. To structure our measurement, we formalize a three-dimensional taxonomy covering linguistic disguise, structural obfuscation, and semantic abstraction, and construct ReadSecBench, a benchmark of 500 real-world README files enabling reproducible evaluation. Experiments on the commercially deployed computer-use agent show end-to-end exfiltration success rates up to 85%, consistent across five programming languages and three injection positions. Cross-model evaluation on four LLM families in a simulation environment confirms that semantic compliance with injected instructions is consistent across model families. A 15-participant user study yields a 0% detection rate across all participants, and evaluation of 12 rule-based and 6 LLM-based defenses shows neither category achieves reliable detection without unacceptable false-positive rates. Together, these results quantify a persistent Semantic-Safety Gap between agents' functional compliance and their security awareness, establishing that documentation-embedded instruction injection is a persistent and currently unmitigated threat to high-privilege LLM agent deployments.

Long-term memory has emerged as a foundational component of autonomous Large Language Model (LLM) agents, enabling continuous adaptation, lifelong multimodal learning, and sophisticated reasoning. However, as memory systems transition from static retrieval databases to dynamic, agentic mechanisms, critical concerns regarding memory governance, semantic drift, and privacy vulnerabilities have surfaced. While recent surveys have focused extensively on memory retrieval efficiency, they largely overlook the emergent risks of memory corruption in highly dynamic environments. To address these emerging challenges, we propose the Stability and Safety-Governed Memory (SSGM) framework, a conceptual governance architecture. SSGM decouples memory evolution from execution by enforcing consistency verification, temporal decay modeling, and dynamic access control prior to any memory consolidation. Through formal analysis and architectural decomposition, we show how SSGM can mitigate topology-induced knowledge leakage where sensitive contexts are solidified into long-term storage, and help prevent semantic drift where knowledge degrades through iterative summarization. Ultimately, this work provides a comprehensive taxonomy of memory corruption risks and establishes a robust governance paradigm for deploying safe, persistent, and reliable agentic memory systems.

Autonomous Large Language Model (LLM) agents, exemplified by OpenClaw, demonstrate remarkable capabilities in executing complex, long-horizon tasks. However, their tightly coupled instant-messaging interaction paradigm and high-privilege execution capabilities substantially expand the system attack surface. In this paper, we present a comprehensive security threat analysis of OpenClaw. To structure our analysis, we introduce a five-layer lifecycle-oriented security framework that captures key stages of agent operation, i.e., initialization, input, inference, decision, and execution, and systematically examine compound threats across the agent's operational lifecycle, including indirect prompt injection, skill supply chain contamination, memory poisoning, and intent drift. Through detailed case studies on OpenClaw, we demonstrate the prevalence and severity of these threats and analyze the limitations of existing defenses. Our findings reveal critical weaknesses in current point-based defense mechanisms when addressing cross-temporal and multi-stage systemic risks, highlighting the need for holistic security architectures for autonomous LLM agents. Within this framework, we further examine representative defense strategies at each lifecycle stage, including plugin vetting frameworks, context-aware instruction filtering, memory integrity validation protocols, intent verification mechanisms, and capability enforcement architectures.

AI agents that combine large language models with non-AI system components are rapidly emerging in real-world applications, offering unprecedented automation and flexibility. However, this unprecedented flexibility introduces complex security challenges fundamentally different from those in traditional software systems. This paper presents the first systematic and comprehensive survey of AI agent security, including an analysis of the design space, attack landscape, and defense mechanisms for secure AI agent systems. We further conduct case studies to point out existing gaps in securing agentic AI systems and identify open challenges in this emerging domain. Our work also introduces the first systematic framework for understanding the security risks and defense strategies of AI agents, serving as a foundation for building both secure agentic systems and advancing research in this critical area.

Large Language Model-based Multi-Agent Systems (MAS) have demonstrated remarkable collaborative reasoning capabilities but introduce new attack surfaces, such as the sleeper agent, which behave benignly during routine operation and gradually accumulate trust, only revealing malicious behaviors when specific conditions or triggers are met. Existing defense works primarily focus on static graph optimization or hierarchical data management, often failing to adapt to evolving adversarial strategies or suffering from high false-positive rates (FPR) due to rigid blocking policies. To address this, we propose DynaTrust, a novel defense method against sleeper agents. DynaTrust models MAS as a dynamic trust graph~(DTG), and treats trust as a continuous, evolving process rather than a static attribute. It dynamically updates the trust of each agent based on its historical behaviors and the confidence of selected expert agents. Instead of simply blocking, DynaTrust autonomously restructures the graph to isolate compromised agents and restore task connectivity to ensure the usability of MAS. To assess the effectiveness of DynaTrust, we evaluate it on mixed benchmarks derived from AdvBench and HumanEval. The results demonstrate that DynaTrust outperforms the state-of-the-art method AgentShield by increasing the defense success rate by 41.7%, achieving rates exceeding 86% under adversarial conditions. Furthermore, it effectively balances security with utility by significantly reducing FPR, ensuring uninterrupted system operations through graph adaptation.

Artificial Intelligence (AI) agents have evolved from passive predictive tools into active entities capable of autonomous decision-making and environmental interaction, driven by the reasoning capabilities of Large Language Models (LLMs). However, this evolution has introduced critical security vulnerabilities that existing frameworks fail to address. The Hierarchical Autonomy Evolution (HAE) framework organizes agent security into three tiers: Cognitive Autonomy (L1) targets internal reasoning integrity; Execution Autonomy (L2) covers tool-mediated environmental interaction; Collective Autonomy (L3) addresses systemic risks in multi-agent ecosystems. We present a taxonomy of threats spanning cognitive manipulation, physical environment disruption, and multi-agent systemic failures, and evaluate existing defenses while identifying key research gaps. The findings aim to guide the development of multilayered, autonomy-aware defense architectures for trustworthy AI agent systems.

Autonomous agents powered by large language models introduce a class of execution-layer vulnerabilities -- prompt injection, retrieval poisoning, and uncontrolled tool invocation -- that existing guardrails fail to address systematically. In this work, we propose the Layered Governance Architecture (LGA), a four-layer framework comprising execution sandboxing (L1), intent verification (L2), zero-trust inter-agent authorization (L3), and immutable audit logging (L4). To evaluate LGA, we construct a bilingual benchmark (Chinese original, English via machine translation) of 1,081 tool-call samples -- covering prompt injection, RAG poisoning, and malicious skill plugins -- and apply it to OpenClaw, a representative open-source agent framework. Experimental results on Layer 2 intent verification with four local LLM judges (Qwen3.5-4B, Llama-3.1-8B, Qwen3.5-9B, Qwen2.5-14B) and one cloud judge (GPT-4o-mini) show that all five LLM judges intercept 93.0-98.5% of TC1/TC2 malicious tool calls, while lightweight NLI baselines remain below 10%. TC3 (malicious skill plugins) proves harder at 75-94% IR among judges with meaningful precision-recall balance, motivating complementary enforcement at Layers 1 and 3. Qwen2.5-14B achieves the best local balance (98% IR, approximately 10-20% FPR); a two-stage cascade (Qwen3.5-9B->GPT-4o-mini) achieves 91.9-92.6% IR with 1.9-6.7% FPR; a fully local cascade (Qwen3.5-9B->Qwen2.5-14B) achieves 94.7-95.6% IR with 6.0-9.7% FPR for data-sovereign deployments. An end-to-end pipeline evaluation (n=100) demonstrates that all four layers operate in concert with 96% IR and a total P50 latency of approximately 980 ms, of which the non-judge layers contribute only approximately 18 ms. Generalization to the external InjecAgent benchmark yields 99-100% interception, confirming robustness beyond our synthetic data.

Agentic systems increasingly orchestrate complex, tool-using workflows within agentic execution environments, where high-level goals and tool invocations at the application layer materialize as process, file, and network activities at the operating-system layer. This cross-layer execution creates security risks that conventional input guardrails cannot capture, because malicious intent may become observable only through downstream execution effects. In multi-agent deployments, inter-agent communication and delegation introduce additional propagation paths. To address this gap, we propose AScope, an execution-aware framework that correlates application-level agent semantics with kernel-level audit events and reconstructs them as cross-layer semantic flows. AScope connects fragmented operations into causal behavioral trajectories and uses a supervisor LLM to identify data flow violations, control flow deviations, and intent inconsistencies. We evaluate AScope on published AgentDojo traces with application-layer evidence and on ten multi-agent scenarios with cross-layer telemetry. The results demonstrate strong detection sensitivity across both evidence settings and achieve node- and path-level F1-scores of 85.3% and 66.7% on the cross-layer dataset.

LLM agents increasingly act on users' personal information, yet existing privacy defenses remain limited in both design and adaptability. Most prior approaches rely on static or passive defenses, such as prompting and guarding. These paradigms are insufficient for supporting contextual, proactive privacy decisions in multi-step agent execution. We propose Contextualized Defense Instructing (CDI), a new privacy defense paradigm in which an instructor model generates step-specific, context-aware privacy guidance during execution, proactively shaping actions rather than merely constraining or vetoing them. Crucially, CDI is paired with an experience-driven optimization framework that trains the instructor via reinforcement learning (RL), where we convert failure trajectories with privacy violations into learning environments. We formalize baseline defenses and CDI as distinct intervention points in a canonical agent loop, and compare their privacy-helpfulness trade-offs within a unified simulation framework. Results show that our CDI consistently achieves a better balance between privacy preservation (94.2%) and helpfulness (80.6%) than baselines, with superior robustness to adversarial conditions and generalization.

Large language models (LLMs) increasingly act as autonomous agents, using tools to execute code, read and write files, and access networks, creating novel security risks. To mitigate these risks, agents are commonly deployed and evaluated in isolated "sandbox" environments, often implemented using Docker/OCI containers. We introduce SANDBOXESCAPEBENCH, an open benchmark that safely measures an LLM's capacity to break out of these sandboxes. The benchmark is implemented as an Inspect AI Capture the Flag (CTF) evaluation utilising a nested sandbox architecture with the outer layer containing the flag and no known vulnerabilities. Following a threat model of a motivated adversarial agent with shell access inside a container, SANDBOXESCAPEBENCH covers a spectrum of sandboxescape mechanisms spanning misconfiguration, privilege allocation mistakes, kernel flaws, and runtime/orchestration weaknesses. We find that, when vulnerabilities are added, LLMs are able to identify and exploit them, showing that use of evaluation like SANDBOXESCAPEBENCH is needed to ensure sandboxing continues to provide the encapsulation needed for highly-capable models.

Colluding language-model agents can hide coordination in messages that remain policy-compliant at the surface level. We present CLBC, a protocol where generation and admission are separated: a message is admitted to transcript state only if a small verifier accepts a proof-bound envelope under a pinned predicate $Π$. The predicate binds policy hash, public randomness schedule, transcript chaining, latent schema constraints, canonical metadata/tool fields, and deterministic rejection codes. We show how this protocol yields an upper bound on transcript leakage in terms of latent leakage plus explicit residual channels, derive adaptive composition guarantees, and state a semantic lower bound when policy-valid alternatives remain choosable. We report extensive empirically grounded evidence: aggregate evaluation satisfies all prespecified thresholds; strict lane decoder advantage is bounded at 0.0000 with MI proxy 0.0636; adaptive-colluder stress tests remain below attacker thresholds; and baseline separation shows large gaps between reject-by-default semantics and audit-only controls. We further quantify operational tradeoffs. Strict full-proof mode has median turn latency 27.53s (p95 28.08s), while sampled proving reduces non-proved-turn latency to 0.327ms. The central finding is that bottlenecks alone are insufficient: security claims depend on verifiable admission semantics that are online, deterministic, and fail-closed.

Agentic large language model systems increasingly automate tasks by retrieving URLs and calling external tools. We show that this workflow gives rise to implicit prompt injection: adversarial instructions embedded in automatically generated URL previews, including titles, metadata, and snippets, can introduce a system-level risk that we refer to as silent egress. Using a fully local and reproducible testbed, we demonstrate that a malicious web page can induce an agent to issue outbound requests that exfiltrate sensitive runtime context, even when the final response shown to the user appears harmless. In 480 experimental runs with a qwen2.5:7b-based agent, the attack succeeds with high probability (P (egress) =0.89), and 95% of successful attacks are not detected by output-based safety checks. We also introduce sharded exfiltration, where sensitive information is split across multiple requests to avoid detection. This strategy reduces single-request leakage metrics by 73% (Leak@1) and bypasses simple data loss prevention mechanisms. Our ablation results indicate that defenses applied at the prompt layer offer limited protection, while controls at the system and network layers, such as domain allowlisting and redirect-chain analysis, are considerably more effective. These findings suggest that network egress should be treated as a first-class security outcome in agentic LLM systems. We outline architectural directions, including provenance tracking and capability isolation, that go beyond prompt-level hardening.

Agentic systems increasingly rely on reusable procedural capabilities, a.k.a., agentic skills, to execute long-horizon workflows reliably. These capabilities are callable modules that package procedural knowledge with explicit applicability conditions, execution policies, termination criteria, and reusable interfaces. Unlike one-off plans or atomic tool calls, skills operate (and often do well) across tasks. This paper maps the skill layer across the full lifecycle (discovery, practice, distillation, storage, composition, evaluation, and update) and introduces two complementary taxonomies. The first is a system-level set of seven design patterns capturing how skills are packaged and executed in practice, from metadata-driven progressive disclosure and executable code skills to self-evolving libraries and marketplace distribution. The second is an orthogonal \textbf{representation $\times$ scope} taxonomy describing what skills are (natural language, code, policy, hybrid) and what environments they operate over (web, OS, software engineering, robotics). We analyze the security and governance implications of skill-based agents, covering supply-chain risks, prompt injection via skill payloads, and trust-tiered execution, grounded by a case study of the ClawHavoc campaign in which nearly 1{,}200 malicious skills infiltrated a major agent marketplace, exfiltrating API keys, cryptocurrency wallets, and browser credentials at scale. We further survey deterministic evaluation approaches, anchored by recent benchmark evidence that curated skills can substantially improve agent success rates while self-generated skills may degrade them. We conclude with open challenges toward robust, verifiable, and certifiable skills for real-world autonomous agents.

LLM agents are evolving rapidly, powered by code execution, tools, and the recently introduced agent skills feature. Skills allow users to extend LLM applications with specialized third-party code, knowledge, and instructions. Although this can extend agent capabilities to new domains, it creates an increasingly complex agent supply chain, offering new surfaces for prompt injection attacks. We identify skill-based prompt injection as a significant threat and introduce SkillInject, a benchmark evaluating the susceptibility of widely-used LLM agents to injections through skill files. SkillInject contains 202 injection-task pairs with attacks ranging from obviously malicious injections to subtle, context-dependent attacks hidden in otherwise legitimate instructions. We evaluate frontier LLMs on SkillInject, measuring both security in terms of harmful instruction avoidance and utility in terms of legitimate instruction compliance. Our results show that today's agents are highly vulnerable with up to 80% attack success rate with frontier models, often executing extremely harmful instructions including data exfiltration, destructive action, and ransomware-like behavior. They furthermore suggest that this problem will not be solved through model scaling or simple input filtering, but that robust agent security will require context-aware authorization frameworks. Our benchmark is available at https://www.skill-inject.com/.

We report an exploratory red-teaming study of autonomous language-model-powered agents deployed in a live laboratory environment with persistent memory, email accounts, Discord access, file systems, and shell execution. Over a two-week period, twenty AI researchers interacted with the agents under benign and adversarial conditions. Focusing on failures emerging from the integration of language models with autonomy, tool use, and multi-party communication, we document eleven representative case studies. Observed behaviors include unauthorized compliance with non-owners, disclosure of sensitive information, execution of destructive system-level actions, denial-of-service conditions, uncontrolled resource consumption, identity spoofing vulnerabilities, cross-agent propagation of unsafe practices, and partial system takeover. In several cases, agents reported task completion while the underlying system state contradicted those reports. We also report on some of the failed attempts. Our findings establish the existence of security-, privacy-, and governance-relevant vulnerabilities in realistic deployment settings. These behaviors raise unresolved questions regarding accountability, delegated authority, and responsibility for downstream harms, and warrant urgent attention from legal scholars, policymakers, and researchers across disciplines. This report serves as an initial empirical contribution to that broader conversation.

LLM agents rely heavily on high-quality trajectory data to guide their problem-solving behaviors, yet producing such data requires substantial task design, high-capacity model generation, and manual filtering. Despite the high cost of creating these datasets, existing literature has overlooked copyright protection for LLM agent trajectories. This gap leaves creators vulnerable to data theft and makes it difficult to trace misuse or enforce ownership rights. This paper introduces ActHook, the first watermarking method tailored for agent trajectory datasets. Inspired by hook mechanisms in software engineering, ActHook embeds hook actions that are activated by a secret input key and do not alter the original task outcome. Like software execution, LLM agents operate sequentially, allowing hook actions to be inserted at decision points without disrupting task flow. When the activation key is present, an LLM agent trained on watermarked trajectories can produce these hook actions at a significantly higher rate, enabling reliable black-box detection. Experiments on mathematical reasoning, web searching, and software engineering agents show that ActHook achieves an average detection AUC of 94.3 on Qwen-2.5-Coder-7B while incurring negligible performance degradation.

LLM agents are increasingly deployed in long-horizon, complex environments to solve challenging problems, but this expansion exposes them to long-horizon attacks that exploit multi-turn user-agent-environment interactions to achieve objectives infeasible in single-turn settings. To measure agent vulnerabilities to such risks, we present AgentLAB, the first benchmark dedicated to evaluating LLM agent susceptibility to adaptive, long-horizon attacks. Currently, AgentLAB supports five novel attack types including intent hijacking, tool chaining, task injection, objective drifting, and memory poisoning, spanning 28 realistic agentic environments, and 644 security test cases. Leveraging AgentLAB, we evaluate representative LLM agents and find that they remain highly susceptible to long-horizon attacks; moreover, defenses designed for single-turn interactions fail to reliably mitigate long-horizon threats. We anticipate that AgentLAB will serve as a valuable benchmark for tracking progress on securing LLM agents in practical settings. The benchmark is publicly available at https://tanqiujiang.github.io/AgentLAB_main.

Tool-using LLM agents increasingly coordinate real workloads by selecting and chaining third-party tools based on text-visible metadata such as tool names, descriptions, and return messages. We show that this convenience creates a supply-chain attack surface: a malicious MCP tool server can be co-registered alongside normal tools and induce overthinking loops, where individually trivial or plausible tool calls compose into cyclic trajectories that inflate end-to-end tokens and latency without any single step looking abnormal. We formalize this as a structural overthinking attack, distinguishable from token-level verbosity, and implement 14 malicious tools across three servers that trigger repetition, forced refinement, and distraction. Across heterogeneous registries and multiple tool-capable models, the attack causes severe resource amplification (up to $142.4\times$ tokens) and can degrade task outcomes. Finally, we find that decoding-time concision controls do not reliably prevent loop induction, suggesting defenses should reason about tool-call structure rather than tokens alone.

Semantic caching has emerged as a pivotal technique for scaling LLM applications, widely adopted by major providers including AWS and Microsoft. By utilizing semantic embedding vectors as cache keys, this mechanism effectively minimizes latency and redundant computation for semantically similar queries. In this work, we conceptualize semantic cache keys as a form of fuzzy hashes. We demonstrate that the locality required to maximize cache hit rates fundamentally conflicts with the cryptographic avalanche effect necessary for collision resistance. Our conceptual analysis formalizes this inherent trade-off between performance (locality) and security (collision resilience), revealing that semantic caching is naturally vulnerable to key collision attacks. While prior research has focused on side-channel and privacy risks, we present the first systematic study of integrity risks arising from cache collisions. We introduce CacheAttack, an automated framework for launching black-box collision attacks. We evaluate CacheAttack in security-critical tasks and agentic workflows. It achieves a hit rate of 86% in LLM response hijacking and can induce malicious behaviors in LLM agent, while preserving strong transferability across different embedding models. A case study on a financial agent further illustrates the real-world impact of these vulnerabilities. Finally, we discuss mitigation strategies.

Autonomous code agents built on large language models are reshaping software and AI development through tool use, long-horizon reasoning, and self-directed interaction. However, this autonomy introduces a previously unrecognized security risk: agentic interaction fundamentally expands the LLM attack surface, enabling systematic probing and recovery of hidden system prompts that guide model behavior. We identify system prompt extraction as an emergent vulnerability intrinsic to code agents and present JustAsk, a self-evolving framework that autonomously discovers effective extraction strategies through interaction alone. Unlike prior prompt-engineering or dataset-based attacks, JustAsk requires no handcrafted prompts, labeled supervision, or privileged access beyond standard user interaction. It formulates extraction as an online exploration problem, using Upper Confidence Bound-based strategy selection and a hierarchical skill space spanning atomic probes and high-level orchestration. These skills exploit imperfect system-instruction generalization and inherent tensions between helpfulness and safety. Evaluated on 41 black-box commercial models across multiple providers, JustAsk consistently achieves full or near-complete system prompt recovery, revealing recurring design- and architecture-level vulnerabilities. Our results expose system prompts as a critical yet largely unprotected attack surface in modern agent systems.

AI agents are autonomous systems that combine LLMs with external tools to solve complex tasks. While such tools extend capability, improper tool permissions introduce security risks such as indirect prompt injection and tool misuse. We characterize these failures as unbalanced tool-driven agency. Agents may retain unnecessary permissions (excessive agency) or fail to invoke required tools (insufficient agency), amplifying the attack surface and reducing performance. We introduce AgenTRIM, a framework for detecting and mitigating tool-driven agency risks without altering an agent's internal reasoning. AgenTRIM addresses these risks through complementary offline and online phases. Offline, AgenTRIM reconstructs and verifies the agent's tool interface from code and execution traces. At runtime, it enforces per-step least-privilege tool access through adaptive filtering and status-aware validation of tool calls. Evaluating on the AgentDojo benchmark, AgenTRIM substantially reduces attack success while maintaining high task performance. Additional experiments show robustness to description-based attacks and effective enforcement of explicit safety policies. Together, these results show that AgenTRIM provides a practical, capability-preserving approach to safer tool use in LLM-based agents.

LLM agents can combine individually non-revealing tool returns and disclose a sensitive conclusion, creating Tools Orchestration Privacy Risk (TOP-R). We formalize TOP-R through three conditions: conclusion sensitivity, single-source non-inferability, and compositional inferability. We introduce Library-Grounded Reverse-Inference Seed Expansion (LRSE), a four-library reverse-construction pipeline, and use it to build TOP-Bench, a 1,000-instance benchmark evaluated under a controlled two-stage tool-use protocol. Across six LLM agents, average task completion, leakage, and H-score are 98.0 percent, 88.6 percent, and 20.4. With native reasoning enabled, four models average 81.4 percent final-response leakage and 82.4 percent reasoning-trace leakage. With reasoning disabled, three prompt-only safeguards improve H-score by an average of about 3.4 points on TOP-Bench. We further propose TOP-Align, an SFT+DPO method for learning safer task-completion boundaries. On a separate post-training evaluation set, TOP-Align improves H-score by 16.2 points over the base model, versus a 5.0-point average gain from prompt-only mitigation on the same set. These results show that TOP-R requires defenses beyond prompting alone. Dataset and code are available at https://github.com/1Ponder/TOP-R.

Large Language Model (LLM)-based Multi-Agent Systems (MAS) are susceptible to linguistic attacks that can trigger cascading failures across the network. Existing defenses face a fundamental dilemma: lightweight single-auditor methods are prone to single points of failure, while robust committee-based approaches incur prohibitive computational costs in multi-turn interactions. To address this challenge, we propose MAS-Shield, a secure and efficient defense framework designed with a coarse-to-fine filtering pipeline. Rather than applying uniform scrutiny, MAS-Shield dynamically allocates defense resources through a three-stage protocol: (1) Critical Agent Selection strategically targets high-influence nodes to narrow the defense surface; (2) Light Auditing employs lightweight sentry models to rapidly filter the majority of benign cases; and (3) Global Consensus Auditing escalates only suspicious or ambiguous signals to a heavyweight committee for definitive arbitration. This hierarchical design effectively optimizes the security-efficiency trade-off. Experiments demonstrate that MAS-Shield achieves a 92.5% recovery rate against diverse adversarial scenarios and reduces defense latency by over 70% compared to existing methods.

Code-capable large language model (LLM) agents are embedded in software engineering workflows where they can read, write, and execute code, raising "jailbreak" stakes beyond text-only settings. Prior evaluations emphasize refusal or harmful-text detection, leaving open whether agents compile and run malicious programs. We present JAWS-Bench (Jailbreaks Across WorkSpaces), a benchmark spanning three escalating workspace regimes mirroring attacker capability: empty (JAWS-0), single-file (JAWS-1), and multi-file (JAWS-M). We pair it with a hierarchical, executable-aware Judge Framework that tests (i) compliance, (ii) attack success, (iii) syntactic correctness, and (iv) runtime executability to measure deployable harm. Across seven LLM backends from five families, prompt-only attacks in JAWS-0 achieve 61% compliance; 58% are harmful, 52% parse, and 27% run end-to-end. In JAWS-1, compliance reaches ~100% for stronger models with a mean ASR (Attack Success Rate) ~71%; JAWS-M raises mean ASR to ~75%, with 32% runnable attack code. Wrapping an LLM in an agent increases ASR by 1.6$\times$, by overturning initial refusals during planning and tool use. Additional evaluations with SWE-Agent and OpenAI Codex exhibit similar trends, indicating that JAWS-Bench can be reused across multiple agent frameworks. Category analyses identify which attack classes are most vulnerable and deployable, motivating execution-aware defenses and refusal-preserving agent designs.

Coding agents powered by large language models are becoming central modules of modern IDEs, helping users perform complex tasks by invoking tools. While powerful, tool invocation opens a substantial attack surface. Prior work has demonstrated attacks against general-purpose and domain-specific agents, but none have focused on the security risks of tool invocation in coding agents. To fill this gap, we conduct the first systematic red-teaming of six popular real-world coding agents: Cursor, Claude Code, Copilot, Windsurf, Cline, and Trae. Our red-teaming proceeds in two phases. In Phase 1, we perform prompt leakage reconnaissance to recover system prompts. We discover a general vulnerability, ToolLeak, which allows malicious prompt exfiltration through benign argument retrieval during tool invocation. In Phase 2, we hijack the agent's tool-invocation behavior using a novel two-channel prompt injection in the tool description and return values, achieving remote code execution (RCE). We adaptively construct payloads using security information leaked in Phase 1. In emulation across five backends, our method outperforms baselines on Claude-Sonnet-4, Claude-Sonnet-4.5, Grok-4, and GPT-5. On real agents, our approach succeeds on 19 of 25 agent-LLM pairs, achieving leakage on every agent using Claude and Grok backends. For tool-invocation hijacking, we obtain RCE on every tested agent-LLM pair, with our two-channel method delivering the highest success rate. We provide case studies on Cursor and Claude Code, analyze security guardrails of external and built-in tools, and conclude with practical defense recommendations.