Tool Access Control for LLM Agents

Security Operations Centers (SOCs) for information technology and operational technology share one incident-response problem: a flood of correlated alerts and too few analysts. Large Language Models (LLMs) are increasingly proposed as reasoning engines that triage alerts and, in autonomous deployments, issue commands that block IPs, kill processes, or quarantine files on production hosts. This coupling introduces a new risk: a single adversarial alert can become a remote code path through the LLM's reasoning, leading it to recommend an action the SOC then executes. We present a constrained-action architecture with two coordinated layers: (i) a SIEM/XDR control plane that grounds remediation in correlated host events and confines the LLM's output to a closed intent vocabulary whose templated commands are executed by thin endpoint agents, backstopped by an argument validator; and (ii) a NeMo-Guardrails proxy that wraps the SOC-analyst LLM with input- and output-rail policies, evaluated out-of-the-box against a SOC-specific adversarial corpus we release. The stock proxy lifts injection recall from 25.0% to 94.5% at a 0.1% false-positive rate, and a live red-team exercise confirms that the closed intent vocabulary and argument validator contain the observed LLM failure modes before any command crosses the trust boundary. As an architectural fit (not yet a measured operational-technology deployment), the constrained-action property suits critical-infrastructure settings where a wrong remediation has physical, not merely operational, consequences. The loop is best run human-in-the-loop or delayed: the measured rail latency keeps inline control out of scope.

LLM-based agents are entering decision-support roles in defence staff work, where the obligations they must respect are already written down and binding, and where retraining is not available as a control because models arrive as procured components. What can be placed under engineering control is the interface between the agent and the systems it acts on. Those obligations are at once spatial, temporal and text-semantic, and a violation typically lives in the composition of a multi-step interaction, which is why per-event guardrails miss sequential tool-attack chains. We present a multi-aspect runtime-verification framework that decomposes a natural-language policy clause into a typed spatial/temporal/semantic triple over one canonical event stream, checks each aspect with its own monitoring specification, and fuses the verdicts through a four-valued algebra that carries provenance. The spatial aspect is interpreted over a weighted two-sorted location graph in which mission geometry and information-release topology are one object; we show that these spatial obligations are not in general subsumed by a first-order temporal specification. The past-time aspect runs on the unmodified MonPoly engine, which agrees with our reference monitor at every time point. Across two mission domains, casualty evacuation and contested sustainment, and one civil domain, composition under the precautionary blocking policy drives attack success to zero with no observed false positives and microsecond-scale per-event cost, while every single aspect and every pair leaves a substantial share of attacks succeeding. In a closed-loop experiment a policy-naive planner reaches a violating state in most unshielded missions and in none when shielded, and four refused episodes in five still recover to a compliant outcome.

LLM tool-use agents operate in dynamic environments where many actions carry operational risk. However, most safety mechanisms react only after errors manifest. Existing pre-emptive approaches either fine-tune the agent on chain-of-thought deliberation or compile natural-language guardrails into runtime checks, but they do so without exposing a structural, auditable verdict. We propose POLAR, a guardrail framework for small tool-calling agents that assesses reversibility through a structured two-layer ontology. POLAR assigns each action a graded reversibility score by deriving a candidate inverse sequence; calls failing a threshold are pruned before execution. Evaluated on $τ^2$-bench across six agent models, POLAR improves mean task reward by 0.11 to 0.18 points on airline for four of six agents, but only eight of eighteen model--domain cells improve overall; retail and stronger agents often regress. POLAR provides an auditable structural check and characterizes its task-utility trade-offs. Reward is not a direct measure of prevented harm.

Many agent runtimes give the agent a tool for editing its own configuration. Some of that configuration grants abilities, such as enabling a tool. Other parts set the agent's limits: which directories it may write to, who may send it messages, which network address it listens on, how callers authenticate, and the gate that blocks risky writes. If the agent can edit those limits, a single ordinary request can widen them. We study this in a deployed, model-agnostic runtime. We propose a rule: the agent may change fields that grant abilities, and may never change fields that set its limits. We enforce the rule as a containment floor inside the configuration tool and measure what happens with and without it. Without the floor, a frontier model wrote a protected value on 25 of 72 ordinary requests that gave it permission to change settings, often when the request never named the field. Prohibitions written in the system prompt failed in a predictable way. A prompt that listed the protected field names stopped every request that used those names (0 of 36 saved, against 17 of 36 with no prompt) and did not stop the requests that only described the goal (10 of 36 saved, against 8 of 36). A prompt that described the forbidden effects did the reverse. With the floor, 0 of 167 protected writes were saved, although the models attempted a protected write in 65 of those cases. A search for other routes through the tool found only one, a pinned shell, which the floor's scope statement already excludes. The study covers two models and a single agent. We state what that does and does not support.

Indirect prompt injection (IPI) hides adversarial instructions in content that large language model (LLM) agents read at runtime. As agents compose heterogeneous capability units, including Tools, MCP servers, and Skills, the carriers of injection multiply, and defenses built to recognize attack patterns fall behind them. We instead shift defense from covering attack patterns to one stable point: whatever the carrier and however the injection propagates, harm materializes only at the \emph{execution boundary}, where the agent turns internal state into an external action or released output. Safety there turns on two conditions, both settled by the trusted task rather than by the run: whether the proposed effect is authorized, and whether the runtime information reaching it is endorsed by that task. We present APEX, an active defense that enforces both at this boundary from a single authorization contract compiled before untrusted execution: \emph{evidence-gated prevention} admits an effect only when the contract justifies it, while \emph{deception-based exposure} makes unendorsed use reveal itself before the effect commits. Protection therefore follows from what the task permits rather than from how an attack is built, and applies uniformly across capability units without attack-specific policies or taint tracking. Against 13 baselines, APEX attains 0% attack success on five of six benchmarks and 0.56% on the sixth, holds 0% under adaptive attacks on all three capability-unit types, and remains effective across defender backbones. Code is available at https://github.com/ZhengXR930/APEX_official/tree/official.

LLM agents with tool-calling capabilities can access external services and private user data, but they may retrieve more information than a user's request explicitly requires. We study this behavior in structured tool-calling agents and term it proactive over-authorization. This setting differs from filesystem-level coding agents because the main risk is unnecessary access to private data. We introduce OverAct, a controlled benchmark spanning eight privacy-sensitive domains with deterministic, judge-free scoring, together with an interpretive decision-theoretic framework that yields three testable predictions. Across seven models from four families, all models significantly exceed authorized scope. Request specificity is the strongest predictor of severity, over-authorization grows sublinearly with tool-pool size, and decoding temperature has little effect. These patterns are consistent with a cost-asymmetry account, suggesting that over-authorization arises more from structural decision tendencies than from decoding randomness. We also propose SelfAudit, a zero-shot inference-time method that generates request-grounded justifications and filters unjustified calls before execution. Ablation shows that explicit filtering is the main driver of scope reduction. SelfAudit reduces privacy-oriented excess by 43% without oracle knowledge.

Tool-using large language model (LLM) agents turn generated text into real side effects, so poisoned tool metadata, retrieved pages, memory, and reusable skills can steer the next call. Vetting an artifact before admission does not settle this. A safe variant and a leaking variant can produce the same admission evidence, and a sound gate then cannot relax that site for either. We make that condition precise, which leaves the last boundary a deployment can still act on. We present Provenance-Aware Capability Enforcement (PACE), which mediates every tool call immediately before it executes. Path confinement proposes an executable cut of represented influence paths, while capability and effect verification checks schema-defined effects against authority compiled from the authenticated request. We distinguish the certified execution contract from the evaluated configuration, which can restore an authorized call after a proposed block or apply a declared repair. Confinement requires the final action to preserve the certified cut. On eight executable agent-security benchmarks with three target-model families, the evaluated configuration gives strictly lowest attack success in 62 of 79 eligible attack columns and ties in 14; full-benchmark native utility loses at most three points relative to the undefended agent. A complete ablation over 1167 paired cases attributes most security gains to effect verification and refusal control to boundary adaptation. A reduced-scale adaptive search succeeds on 0/30 out-of-authority targets against the defense.

Contextual security defenses prevent AI agents from taking rogue actions by synthesizing a task-specific policy and enforcing it on the agent's tool calls. In multi-step tasks, however, which actions are valid often depends on what the agent has already done and learned. We present Sapien, a policy engine for enforcing stateful contextual policies. A Sapien policy specifies permitted tool-call sequences using a regular expression extended with stateful predicates, deferred policy generation, and scoped semantic checks. We show that Sapien stays within a few percent of an unconstrained agent's utility. Even if the agent is fully hijacked, Sapien's policies rule out 93-95% of attacks on AgentDojo and 62-85% on Toolathlon (twice as many as tool allowlists on long-horizon tasks).

Modern AI coding-agent harnesses (Claude Code, Codex CLI, Cursor) rest their security boundary on a largely unexamined assumption: that the action A a human approves is the same action A' the harness executes, where A is fixed by a stated policy for what a scope grant or session-scoped approval authorizes. We show this assumption fails systematically and reproducibly. We introduce Approval Laundering, a taxonomy of six failure modes by which a harness's enforcement mechanism silently substitutes A' for A after approval: Scope, Argument, Temporal, Tool, Delegation, and Semantic laundering. Unlike prior work that evaluates risk classifiers against static corpora or infers implicit authorization boundaries, we study credential-binding integrity: given an already-approved action, does the harness dispatch exactly that action? Instrumenting Claude Code's pre-execution mediation point (PreToolUse), we conduct a controlled, headless, repeated-measures study of all six classes (N=19-20 runs each), reporting a Bound-Gap Rate (BGR) with Wilson confidence intervals and inter-rater agreement (kappa=1.0). We prototype Approval Token, a keyed capability Hk(principal, agent_id, session_id, tool, arguments, scope, expiry) issued by a mediator that never returns the key to the agent, evaluated via paired before/after replay of 118 runs (McNemar's exact test). The token fully eliminates Delegation laundering and, for our seeded session-identity-mismatch construction, Temporal laundering (p<10^-5), but by design leaves Scope laundering unaffected and shows no significant reduction in Argument laundering (p=1): an honest negative result, since these two classes leave every recorded dispatch field unchanged, diverging one process level below what a field-only verifier can observe. We discuss implications for defenses that bind only at the tool-invocation boundary.

Agentic large language models (LLMs) now move money through tools, yet the record of what they did is usually a trace their own process emits beside the effect. Janus puts the record on the effect path. A step's proposal, the verdict on it and any answer from a validator or a person are durable in a signed, hash-chained log before the step may run or its effect be released; with keys declared, each answer is signed by whoever gave or relayed it. Gates are pure functions of that log, and an auditor re-derives every verdict offline from the log and one public key. At the MCP edge the effect is held until then; through the SDK, which our model experiment uses, a cooperating client runs it only afterwards. We evaluate Janus under crash injection (144 kills in-process, 81 through the daemon), by verifying a 100-million-event log offline (254.5 s), and with a real model behind a lending workflow, run governed and plain on the same recorded model outputs. With the lending mandate in the model's prompt, the comparison was 0 against 0. With it only in the policy and the amount's unit stated, the model approved six loans declared over the mandate, three with no injection (a run that also dropped the unit approved three); the plain agent paid all six and Janus none, each refused by a deterministic validator and re-derivable offline. An always-approve oracle over the recorded intakes gave 20 and 21 declared over the mandate against 0, though Janus paid four and three whose declared amount understated the request. Designing the experiment exposed, in a system that passed its own audit, an instance of post-approval substitution: an approval keyed to an attempt was counted for a different proposal, moving a person's approval from 100 to 1,000,000. We report it, a first fix and the five routes around it, and what Janus does not guarantee.

Tool-using LLM agents remain vulnerable to indirect prompt injection because trusted instructions and untrusted observations share one context, allowing malicious content to steer consequential input-filtering defenses. Multi-path consensus defenses still leave a high attack success rate because they examine content or aggregated outputs rather than authorizing effects, especially for the within-tool attack, which preserves the intended tool but manipulates its arguments. Data-Flow Control such as CaMeL provides stronger guarantees, but incurs substantial time latency that limits practical deployment. We introduce ToolFence, which compiles a typed authorization blueprint before execution, enforces it through a deterministic monitor, and when the blueprint is incomplete asks a judge to grant new capabilities rather than adjudicate each concrete call. ToolFence provides two key advantages. First, its fine-grained provenance-aware authorization enables the system to distinguish user-authorized values from untrusted observations, effectively addressing the within-tool attack. Second, its deterministic fast path and capability-level runtime grants substantially reduce the frequency of expensive judge calls, improving runtime efficiency. On AgentDojo with Qwen3-max, ToolFence reduces overall ASR to near zero with only a 3.80 percentage-point clean-utility drop and practical runtime overhead.

The compiler must read modules a physics-based solver cannot build without; the coding agent must not read that intellectual property. The harness does not ship that rule. We classified fifteen read routes against a container, permission rules and a sandbox. None of the three can tell which program is reading.

Tool-enabled agents form calls from model-visible interfaces, while hosts later select their implementation. Standard dispatch omits the descriptor-handler relation. An unchanged and schema-valid call can therefore acquire a different security effect during rollout, reconnect, or delayed approval. We call this failure schema-epoch drift. We present formation-consistent dispatch (FCD), which connects implementation analysis to execution authority. Reviewed profiles produce provenance-bound over-approximations of declared in-scope effects from official source. Under a closed-target approval policy, a verifier applies each formed call to a summary and captures a successor only when its effects fit the call's security contract. Atomic admission and a final-hop fence preserve this decision to the effect. The exact source retains priority, and the captured successor becomes eligible only after source retirement. Stock releases and deployment changes reproduced the failure. Four profiles covered 32 official releases: 29 required no release-specific change and three escalated. A frozen 16-release expansion matched a separate source oracle. In a preregistered stock comparison, FCD completed all three pending calls whose effect remained private and blocked all three whose omission became public. Exact pinning and release-wide denial stopped all six calls, while release-wide approval completed all six but produced three public effects. A separate lifecycle experiment carried a formation-captured certificate across source retirement. The same safe certificate installed later governed new formations without expanding the pending call's authority.

LLM agents operate in persistent collaborative environments involving multiple users, communities, memories, files, and tools. Community boundaries may remain fixed or evolve with changes in membership, roles, composition, and relationships. Agents must complete legitimate tasks and prevent unauthorized disclosure of protected information. Existing evaluations do not fully examine these risks in agent systems. We introduce \textbf{CoSec}, an executable benchmark for evaluating privacy and authorization enforcement in LLM agent systems operating within and across communities. CoSec contains 208 canonical scenarios spanning fixed and evolving boundaries, protected information belonging to the agent owner or other participants, and attacks through dialogue, environmental content, persistent memory, and composed workflows. CoSec executes complete agent systems with persistent sessions, memory, files and tools. It verifies information flows against the active authorization state using execution traces and artifacts. Across harness and model configurations, agents frequently complete benign tasks but violate privacy and authorization boundaries. Privacy behavior varies across harnesses, attack surfaces, and community states, revealing how memory, files, tools, and workflows can carry protected information beyond its authorized scope. These findings show that task utility does not imply privacy or authorization compliance and that authorization in community settings remains an unresolved security challenge for persistent LLM agents.

LLM agents increasingly rely on user approval to authorize security-sensitive actions at runtime. Such approvals are granted within a specific task and execution context. In long-lived agents, authorization decisions may need to persist across tasks or sessions. We find that this continuity can outlive the context that originally justified the approval, creating residual authority reusable without renewed consent. We expose this failure mode through a longitudinal attack that starts from a target security-sensitive action, identifies the authority required to execute it, induces benign interactions that legitimately obtain that authority, and later replays the residual authority during adversarial execution. Across controlled and live settings, we demonstrate that residual-authority replay arises in practice and substantially increases the success of prompt-injection and context-rebinding attacks. We evaluate 508 AgentDojo attack cases across six LLM families using production-derived authorization semantics. With residual authority, attack success rate (ASR) increases by up to 35.1 percentage points compared with a fresh authorization state. In live context-rebinding attacks on 55 Terminal-Bench cases across three real-world production coding agents, residual-authority replay increases ASR by 24.9 percentage points on average. These findings expose a fundamental mismatch between persistent authorization and the contextual nature of user consent in long-lived LLM agents.

Tool-using large language model (LLM) agents turn credential hygiene from a storage problem into an execution-security problem. A key pasted into a prompt, or embedded in a system prompt or tool configuration, crosses from an authentication boundary into a data pipeline, where it may persist in conversation history, logs, memory stores, generated code, and error payloads. Prompt injection and excessive agency then convert passive disclosure into unauthorized action. This paper formalizes the credential-exposure threat chain for agentic systems; synthesizes evidence from a platform secret-store incident, vendor-reported secret-sprawl measurement, and OWASP and NIST guidance; and describes a vault-mediated execution architecture in which the model selects a connector identifier while a trusted request boundary supplies authentication. We evaluate a production implementation, Corvic Security Vault, in two controlled black-box experiments. Across 16 probes spanning seven control domains, every probe met its expected outcome: an authenticated GitHub API request succeeded while the credential stayed absent from process environment values, caller-visible request headers, tested filesystem locations, three third-party echo services, and two unrelated API origins; both cloud instance-metadata endpoints were unreachable. We also report a negative result, a connector whose stored header mapping did not satisfy its provider's authentication contract, showing that centralized custody does not by itself guarantee correct configuration. Vault mediation removes several disclosure paths but is necessary rather than sufficient: least privilege, deterministic action authorization, human approval, telemetry redaction, and rotation remain independently required. The study is purposive and small, a functional security evaluation rather than a certification.

Dataspace connectors decide whether a transfer may occur, not what the transferred value contains, tolerable for contracted applications, not for LLM agents that compose tool calls. Work on agents that generate governance artifacts evaluates output quality, not who may authorize an artifact for use. A published policy is what the decision point enforces, so publication is a governance event, and agents that are both policy subjects and policy authors write the norms that bind them. We name this the authorship hazard and state one principle: an agent is a subject of the governance plane, never an author of it. Its authorization channel to publication is closed by construction; its influence channel, drafting what humans approve, becomes an enforcement problem. Across 90 preregistered edits to the paper's running agreement, each evaluated on 344,512 requests, the six that only reclassify a field all change authorization and narrow a duty without touching policy text, and a policy-diff classifier passes all six. Read as worded, the privilege-delta conditions also pass 33 of 69 effective policy-text edits; read as covering any relaxation, none. Treating classification as authorship routes all six to review; the registry this requires is not yet built. At the execution boundary, protected fields reach the model in 105 of 105 cases under prompt-stated duties and in 0 of 105 under a compiled tool-call constraint, but values outside named fields are exposed in 7 of 7. At the review share measured, a central approval pool needs one approver per 20 to 138 participants.

Large Language Model (LLM) agents struggle to scale safely when exposed to vast enterprise toolsets. Providing an agent with access to every internal tool leads to oversized context windows, degraded tool selection, and severe governance vulnerabilities - as system policies defined purely in prompts remain probabilistic advice rather than hard constraints. Existing mitigations, such as multi-agent domain delegation, decentralize audit logs and fail to guarantee policy compliance across sessions. We introduce skilder, a framework that packages capabilities into roles: bundles of skills, tools, and instructions, together with the limits that bound them. An agent begins with a minimal role catalog, learns the roles a task requires, and receives each role's skills, instructions, and tools through a single MCP server. Because tools reach the agent only inside learned skills, the same server enforces the scope of what was learned deterministically. We evaluate skilder against flat-context tool selection and multi-agent orchestration across 13 tasks using six models (10 runs each). Our results show that, when models completed discovery and issued a governed call, the skilder simulated authorization layer enforced governance boundaries: no unauthorized tool call or parameter violation (e.g., a spending-limit breach) executed. Aggregate task pass rates also reflect whether each model followed the discovery protocol and satisfied response-quality checks; those misses are not authorization failures. Furthermore, by allowing agents to dynamically acquire cross-role capabilities mid-task, skilder preserves problem-solving flexibility while providing hard system-level enforcement.

Generative AI (GenAI) applications have flourished enabling users to chat with large language models, and to create agents to act on their behalf for a variety of tasks. The pace of development of capabilities in this field is incredibly fast with security and safety taking a back seat. Unfortunately, the slower pace at which security and safety mechanisms have evolved has led to real incidents. Policy enables the definition of desirable behavior of applications, and for that reason, it is a cornerstone of making systems secure and compliant. Policy however means different things to different practitioners creating confusion and siloed solutions that are not adequate for compliance. This paper takes a tour of the good, the bad and the ugly when it comes to policy enforcement in GenAI applications. We propose a methodology to systematically analyze and dissect existing approaches to define and enforce policy found in the wild. Based on this principled analysis, we provide recommendations and call for action for the community to address. This paper is a companion extension of USENIX Security 2026 Enigma talk titled "From Alignment to Access Control: A Unified View of GenAI Policy Enforcement" by the author Nathalie Baracaldo.

Moving authorization earlier can shorten an agent's dispatch boundary without removing authorization work. It can also admit an action whose payload, authority, or relevant state has changed. ZeroGate separates exact-action approval from durable local admission: an issuer signs a short-lived ActionPass, and a trusted runtime adapter reconstructs the final action before a local gate checks its binding and consumes its nonce. A SQLite transaction couples nonce consumption, applicable quota updates, and an admission receipt. We state a conditional decision-preservation proposition: successful local admission implies that a specified synchronous policy would authorize the same action at the admission point, provided approval is sound, all policy dependencies are represented and current, observations are faithful, and consumption is atomic. The implementation alone establishes neither current-world freshness nor exactly-once remote effects. Evaluation separates authored semantic fixtures, controlled concurrency and crash experiments, and an Azure Blob study comparing synchronous and prepared execution through the same issuer and gate. Both modes mint an exact-action pass; lifecycle latency includes preparation and prepared-batch dwell. Across 4800 cloud attempts, prepared worker-admission-to-dispatch p95 ranges from 9.802 to 11.374 ms, versus 25.018 to 334.000 ms synchronously, across the tested concurrency levels. Prepared mean complete lifecycle is longer at every level: the boundary improvement is not a net speedup. The contribution is an explicit revalidation contract, a durable reference boundary, and an auditable comparison of where authorization cost is paid, not a new cryptographic primitive or a universal performance frontier.

Large language model (LLM) agents increasingly execute long-horizon workflows through external tools, allowing untrusted outputs to influence subsequent actions and exceed user authorization. Existing defenses isolate injected content or constrain execution with predefined plans and static policies, but these approaches are brittle under dynamic workflows and scale poorly across extensible tool ecosystems. In this work, we present ActGov, a runtime enforcement framework that validates each LLM-proposed tool action before it causes external effects. Built on a unified semantic model of authorization, actions, runtime context, and security constraints, the ActGov-Policy component iteratively constructs a policy set from tool specifications, benign tasks, and observed failure traces, with each update verified through SMT-based counterexample checking. At runtime, ActGov-Runtime abstracts each tool call into finite policy records and permits it only if it remains within the task-scoped authorization boundary and satisfies all applicable policies. This per-action enforcement preserves authorization throughout long-horizon, dynamically branching workflows. We evaluate ActGov on the AgentDojo and AgentDyn benchmarks across multiple models and attack configurations. It shows that ActGov consistently reduces the success rate of indirect prompt-injection attacks while preserving task utility, significantly outperforming existing defenses. These results demonstrate that ActGov can enforce fine-grained authorization over dynamic agent executions without relying on the underlying LLM to correctly identify malicious instructions.

Large language models (LLMs) are increasingly integrated into vehicle voice assistants. But linking natural-language requests to vehicle functions creates a safety-critical authorization problem. Before executing a command, the system must choose whether to execute, refuse, clarify, require confirmation, defer to manual control, trigger an emergency response, or make no tool call. To our knowledge, prior evaluations do not isolate this pre-action decision across speaker role, authentication status, vehicle state, and tool availability. We introduce a 202-scenario benchmark with Reference Decisions under a seven-class taxonomy. We evaluate two local open-weight models and three API-based LLMs using Decision Alignment and safety-specific error metrics. Alignment ranges from 40.1% for Llama 3.2 3B to 89.1% for Gemini 3.1 Pro Preview. The API-based models score between 83.2% and 89.1%, with no statistically significant differences among them. Even these models produce two to three False Executes among 161 non-execution scenarios, and persistent errors remain in confirmation and manual-control decisions. A controlled Llama 3.2 3B ablation increases alignment to 40.1% under the structured authorization policy, versus 28.2-29.2% under schema-only and generic-safety baselines, but it does not eliminate False Executes. Structured LLM decisions are therefore insufficient as a standalone safety mechanism, and deployment requires an independent enforcement layer that verifies tool permissions and vehicle-state constraints before invoking any vehicle function.

Large Language Model (LLM) agents have demonstrated impressive capabilities across a variety of domains, particularly when integrated with external tools for multi-step task completion. However, they are increasingly vulnerable to adversarial attacks, including direct prompt injection, indirect prompt injection, memory poisoning, and backdoor attacks, which exploit the model's openness to prompt injection and tool manipulation. In this work, we explore practical and generalizable defense strategies within a unified framework across these four attack types. We introduce two universal tool-based defenses: Attacker Tool Filtering, which uses anomaly detection (e.g., Isolation Forest) to identify and remove suspicious tools, and Normal Tool Recalling, a white-box method that restores the agent's original toolset prior to planning. Additionally, we incorporate prompt-based defenses: Chain-of-Thought prompting and self-reflection techniques to enhance reasoning and task paraphrasing to mitigate attacks. Experimental results across both four open-source LLMs (Gemma2-9B, Qwen2-7B, LLaMA3-8B, and LLaMA3.1-8B) and three proprietary LLMs (GPT-3.5, GPT-4, and GPT-5) show that our methods significantly reduce the Attack Success Rates (ASR), achieving 0% ASR in many settings, while preserving or even improving the original task success rate. These findings highlight the promise of simple, modular, multi-layered defenses for strengthening the security and robustness of tool-integrated LLM agents. The code is available at https://github.com/Xiaoyan-Lisa/Defenses-for-Tool-Integrated-LLM-Agents-Against-Adversarial-Attacks.

AI agents are provisioned the same as employee-owned hosts in many enterprise settings with a static credential set fixed at deployment which includes all permissions the employee role might ever need. Role-based access control made this compromise for human principals because scoping access per task was infeasible. For AI agents, the compromise leaves every credential standing exposed whether or not the current task uses them. These permissions can later be utilised by a compromised or misaligned agent. Prior work (Noyan, 2026) defined this as the task-context mismatch, and proposed a three-source permission architecture which includes role-based permission ceilings, a task permission classifier and policy-based prohibitions, together eliminating the exposure preemptively. The work released a 600-prompt labelled dataset to evaluate it. This paper presents that evaluation end to end by implementing the security gate; a fine-tuned RoBERTa-large encoder which matched few-shot trained Claude Haiku 4.5 on classification quality (macro-F1 0.881 against 0.886, precision 0.897 against 0.842, severity-weighted residual risk 0.63 against 1.12). The results show the trusted component does not need to scale with the agent it supervises, and the scalable-oversight margin for this control method is wide. We also propose an attack-surface elimination metric which shows the role ceiling alone closes 27.9% of the severity-weighted surface and adding the task classifier closes 84.4%. The gap displays security advantages of task-granular access control over role-granular, and AI agents are the first principal type for which the task-granular access control is enforceable because their tasks arrive as machine-readable text. The research establishes task-based access control as a measured, potentially deployable mechanism for reducing attack surface in agentic deployments.

Multi-tenant tools commonly accept a tenant identifier and validate it against the caller's entitlement. For a large language model (LLM) agent, that pattern delegates resource selection to a process whose context may contain attacker controlled instructions. We formalize this stochastic deputy problem and present a structural defense: remove tenant identity from the Model Context Protocol (MCP) tool schema, bind scope to a verified credential, and enforce it below the agent. In a 373-trial ablation across eight model configurations and two transports, a correctly validated tenant parameter served every out-of-scope attempt: 26 of 26, or 26 of 41 plausible-pretext trials overall. With the parameter removed, no tool signature could express the read. Twelve of 56 trials instead escaped the interface by forging writable scope, showing that interface invariance requires cryptographically protected context. On a production dataset containing multiple GBs of data, set-valued scope caused a measured $57\times$ latency ratio under function-wrapped membership predicates; a JSON_TABLE lateral join recovered index access where the tenant key was indexed. The evaluation also exposes deployment limits, including an entitlement-size query-planner cliff and incomplete index coverage. The result is a tenant-isolation argument that depends on enforceable interfaces and credentials rather than model compliance.

Stateful agents reuse artifacts after producing executions and permissions change. We formalize authority-sufficient observations and durable effects bound to execution and material identities. WTB implements this interface through runtime adapters, shared evidence, and transactional publication/recovery. Six study families separate the mechanism from its integration. Raw and typed evidence both solve 32/32 authority cases, with model-dependent planning effects. Fixed-intent enforcement blocks six unsafe proposals and executes 12 eligible authorized intents. Complete controls match WTB's capability. Paid integration yields 176/210 accepted benchmark-source stages, including 19/30 publication stages, recovery on 8/8 primary SWE repositories, and the most complete continuous trajectories on each of three source tasks. The findings connect authority information, effect admission, and infrastructure reuse in stateful agents.

A runtime gate for an LLM tool agent is usually cast as a filter. In a ReAct loop a rejected proposal is followed by another at the same state, so the gate is a search operator over the proposal stream whose admission criterion shapes which trajectories are reachable. We study post-violation recovery admission, where progress must be admitted while the system is still in violation, and identify the scalar projection trap: an aggregate-score gate accepts a locally improving proposal and commits the trajectory to a plateau. SiLR instead shadow-executes each proposal and admits it under a product order over the branch-level violation state (overloaded-branch support and per-branch severity). We prove that no scalar surrogate is sound for this order, so the failure is representational, not a matter of threshold tuning. On mined Gym-ANM scenarios, SiLR recovers 21/21 multi-action episodes against 0/21 for terminal and 9/21 for the best scalar gate, significant across the full 24-scenario benchmark. The terminal-versus-structured dichotomy holds across three model families and in CityLearn. Because admission rests on deterministic simulation, the LLM lies outside the trust boundary: a magnitude-redistribution attack that defeats both scalar and support-only baselines is contained only by the full per-branch predicate. With two constraint families active, every tested scalar projection admits physically unsafe actions; support-only admits the largest fraction (63.2% of 42,410; product order 0). In the hardest dual-family traces, scalar gates recover only through that unsafe class. Reused as a GRPO process reward, it outperforms its count projection in every mined scenario and is the only tested reward whose ungated policy exceeds the untrained base (0.844 vs. 0.778). Scalar projection loses the violation geometry at both design points; only the full product order is structurally sufficient.

Recursive LLM agents can broaden their search by spawning specialists. Some branches later request tools that send data or deploy code. When should a branch receive authority to act? We distinguish sandbox spawning, in which external controls prevent the specified harm, from capability activation, in which a selected branch crosses an irreversible-action boundary. Progressive Risk Vesting (PRV) holds a trajectory-level risk budget in escrow and debits it as branches are activated. We prove an anytime harm bound for adaptively generated trees. Branch outcomes may be dependent, but each local certificate needs to remain valid conditional on the full pre-activation history, including the information used to select the request. When activation gates, branch charges, and compute constraints are held fixed, delayed vesting preserves every policy available under irrevocable spawn charging. Marginal risk estimates can still fail after branch selection. In a stylized branching model, trajectory harm changes as the authority reproduction number $\mathcal{R}_A$ crosses one. As local risk $p$ approaches zero, trajectory harm is proportional to $p$ below criticality, proportional to $\sqrt{p}$ at criticality, and retains a positive floor above it. A finite-type occupancy model yields risk and compute shadow prices. For nested fanout modes with decreasing marginal value per unit risk, these prices produce a threshold rule. Branching calculations and a split-sample experiment illustrate the results. These synthetic studies do not estimate safety in deployed agents. The analysis suggests a design rule: search broadly in the sandbox and grant recursive authority sparingly, with an explicit risk charge.

Autonomous LLM agents increasingly act on a user's behalf: they hold credentials, call tools and services, and spawn sub-agents that act further on their behalf. This turns a long-standing distributed-systems question -- who is authorized to do what, on whose authority -- into an urgent and largely unsolved problem, because the component driving each agent is a language model an adversary can hijack. We argue that agent security must be evaluated under an untrusted-model assumption: a correct system is one in which a fully prompt-injected agent still cannot exceed the authority explicitly delegated to it. Against this standard we make three contributions. First, we give a threat model for multi-agent delegation centered on four adversaries -- confused deputy, token theft and replay, prompt-injection privilege escalation, and compromised sub-agents -- and derive eight security requirements a governed agent system must meet. Second, we show the gap is real: a default agent runtime modeling common practice (broad bearer credentials, authorization gated inside the model) fails all four threats, and across four widely used frameworks -- LangGraph, CrewAI, AutoGen, and the Model Context Protocol (MCP) authorization model -- three provide no built-in confinement and one only partial; no existing standard alone covers the requirement set. Third, we implement and adversarially evaluate an authorization broker that closes the gap. It blocks all four threats; it resists 11 direct attacks on its design and accepts 0 of 200,000 forged tokens; it confines a compromised sub-agent to its delegated task (a mean of 1.5 reachable actions versus all 8,100 under bearer delegation, across 2,000 randomized scenarios); and it enforces at microsecond cost (about 2.6 microseconds per decision), negligible against model inference. These principles are also realized in production in VotalAI's LLM Shield.

Modern agent frameworks compose planners, tool agents, remote services, and shared specialists into runtime delegation graphs, but their revocation APIs still resemble token or subtree invalidation. When one delegation is withdrawn, the runtime must know which agents lose authority while independently authorized agents keep working. We study this authority consistency problem and introduce VERA (Verifiable Edge Revocation for Agents), a verifier-checkable revocation contract and API emitted by agent-runtime adapters as signed evidence. Under disjunctive authority, revoking edge e invalidates exactly T_intent(e,G) = reach(G) \ reach(G \ {e}), the agents whose every authorizing root path used e. Used as a contract, this target exposes two runtime failures: tree cascades over-revoke shared agents, while deployer-scoped cascades under-revoke cross-domain descendants. In a LangGraph framework-replt cells repeated 20 times yield 500compiled-framework traces and 2,000 valid signed delegation decisions; 13/25 cells contain runtime multi-parsharing and 8/25 contain cross-deployer shies 500/500 target proofs, preserves all320 alternate-parent shared-agent cases that tree cascade revokes, and rejects unauthorized signers and omission attacks. Baseline replay over 1,9that holder/node and tree-style targetscannot express this behavior. We further validate schema portability on A2A, AutoGen, and CrewAI artifacts: nine traces, including five executable Cregned delegation events that pass schema and signature checks.