Tool Access Control for LLM Agents

LLM: Large Language Model

Ask about this topic

Overview

This field studies how to ensure an LLM agent uses only the tools and permissions justified by a user's task, across settings such as APIs, browsers, coding environments, and MCP-based systems. Common approaches include task-scoped least-privilege policies, capability-based delegation, provenance and information-flow tracking, and runtime gateways that check calls before execution or commit; human approval is often reserved for consequential actions. Evidence shows that prompts and static tool allowlists can leave gaps, especially when calls change meaning across steps, permissions persist, or authorization is not bound to the exact action and current state. A central challenge is balancing strong, verifiable restrictions with useful autonomy, while evaluating both unauthorized effects and unnecessary denials in realistic, long-running workflows.

Latest papers

CardsList

222 papers42 papers in the last four weeks, up 8% on the four weeks before. 0.2% of all new papers.

Jul 1, 2026

Janus: a Playground for User-Involved Agentic Permission Management

AI agents that autonomously execute tool calls on a user's behalf raise pressing questions about permission management: what role could users play, and what role should they play? Despite many proposed approaches, the user's role in agentic permission management remains underexplored. We introduce Janus, a playground system for implementing and evaluating user-involved agentic permission management designs. Janus consists of two components: Janus-Core, a modular agentic system supporting a diverse spectrum of permission management designs, and Janus-Harness, an automated evaluation framework. Grounded in a conceptual model that identifies key design axes for user involvement, we implement six permission assistants spanning the design space and evaluate them across three scenarios with four subscenarios each and three synthetic responders. We demonstrate that user involvement is critical and can strengthen privacy and security and that user behavior such as permission fatigue must be accounted for in system design. No single design performs optimally across all contexts, motivating a more principled and context-sensitive approach to deploying permission assistants in agentic systems. Janus is publicly available to support future investigation into this dimension of agentic system design.

Natalie Grace Brigham, Eugene Bagdasarian, Tadayoshi Kohno +1

University of Washington · University of Massachusetts Amherst · Georgetown University

AI Agent SecurityHuman-AI Decision MakingTool Access Control for LLM Agents
AskPDF
Jun 30, 2026

ClawArena-Team: Benchmarking Subagent Orchestration and Dynamic Workflows in Language-Model Agents

Production large language-model (LLM) agents are increasingly deployed not as lone problem-solvers but as managers: a main model creates specialized subagents, delegates work, and orchestrates their parallel, asynchronous returns through dynamic workflows. Whether one model can actually run such a team is largely unmeasured: existing benchmarks score a policy's own task-solving or a fixed multi-agent system's emergent behavior, but none isolate the management ability of the single LLM acting as leader. We introduce ClawArena-Team, a benchmark of 41 multi-turn, multimodal, multi-directory scenarios spanning 258 evaluation rounds and 72 staged updates that measures this management ability. The main agent is deliberately constrained: it natively perceives only text and directly accesses only part of the workspace. It commands a fixed, locally served subagent pool, so score differences reflect management skill, not raw capability. All scoring is execution-based with no LLM judge: an overall score -- the Subagent-Management Score (SMS) -- multiplies task correctness by a least-privilege and modality-routing factor. Across twelve proprietary, community-hosted, and self-hosted models, experiments show that the management bottleneck is privilege granting rather than perception (no model exceeds 50% workspace-permission precision); that cost and management quality are decoupled (API cost spans over 100 times while the overall score spans under 4 times, with the cheapest open models on the Pareto frontier); and that most leaderboard scores cluster within a 9.9-point band while orchestration behaviors diverge by more than an order of magnitude. Code is available at https://github.com/aiming-lab/ClawArena.

Kaiwen Xiong, Haonian Ji, Shi Qiu +4

1UNC-Chapel Hill · University of California, Berkeley · University of California, Santa Cruz

LLM Agent OrchestrationLLM Agent EvaluationAI Agent BenchmarksTool Access Control for LLM Agents
AskPDF
Jun 29, 2026

Behavioral Governance for Autonomous AI Agents: The AgentBound Framework

Autonomous AI agents increasingly perform consequential actions on behalf of human principals, including financial transactions, external communications, and enterprise workflows. Existing agent infrastructure relies on identity federation and delegated authorization to authenticate workloads and control resource access, but it cannot determine whether an authorized action should be executed under the current behavioral and operational context. We present AgentBound, a runtime governance framework that provides verifiable behavioral oversight for autonomous AI agents. AgentBound evaluates each proposed action using three independent authorities: delegated authorization, owner-signed behavioral constitutions, and site action contracts. Their judgments are conservatively composed through a formal decision model to determine whether an action should be permitted, reviewed, or denied before execution. To provide accountability, AgentBound generates cryptographically verifiable governance receipts that bind every action to the exact delegation, policy, and semantic artifacts governing the decision, enabling independent replay verification and policy provenance. The framework also introduces standing delegation for long-running agents, allowing periodic workloads to operate under continuously refreshed governance policies while preserving revocability and bounded authority. We present the formal foundation, system architecture, governance receipt protocol, and AgentBound-Bench, a benchmark framework for evaluating governance correctness, authority composition, and accountability. Rather than replacing model alignment, AgentBound complements it by providing a deterministic governance layer between authorization and execution, transforming governance from a process that must be trusted into one that can be independently verified.

Anuj Kaul, Qianlong Lan, Pranay Gupta

eBay Inc. · Independent Researcher

AI AccountabilityAI Agent GovernanceTool Access Control for LLM Agents
AskPDF
Jun 29, 2026

ATM: CID-Brokered Pre-Write Admission for Multi-Agent Code Co-Synthesis

Multi-agent LLM systems can decompose software-engineering work into planning, generation, validation, and repair, but a narrower systems problem remains: before any governed shared mutation is applied, a system must decide which concurrently formed write intents may proceed in parallel, which require deterministic composition or serialization, and which must take a fail-closed path. We address this problem with the AI-Atomic-Framework (ATM), a specification-grounded governance substrate for software agents operating within a single governance domain. ATM binds task intent, repository scope, write admission, validation, and evidence obligations into one governance chain. A Content Identifier (CID) broker serves as the shared-mutation admission subsystem. Adapter-guided atomization maps write intents to semantic atoms and bounded regions; when persistent atom-map coverage is incomplete, virtual atoms provide temporary auditable governance units for conservative comparison and routing. Governed shared writes are ultimately applied by a neutral steward rather than directly by proposing agents. Evaluation combines controlled, field, adoption, and extension evidence, including a 12-scenario deterministic design matrix, three archived runner cases, ATM-AdmissionBench, three archived same-file boundary cases, a three-week external-adopter study, and an operational recovery-routing benchmark. The results support feasibility, auditability, and bounded recoverability within the observed single-domain settings, but do not claim broad comparative superiority or cross-clone governance.

Eagl Huang

Eagl Huang

Multi-Agent CoordinationSoftware Engineering AgentsAdmittance ControlMulti-Agent ControlAI Agent GovernanceTool Access Control for LLM Agents+1
AskPDF
Jun 27, 2026

From Tool Connection to Execution Control: Benchmarking Security Invariants in MCP-Style Agent Runtimes

Model Context Protocol (MCP)-style ecosystems give language-model applications a practical connection layer for tools, resources, prompts, and transports. As agents move from connection to execution, security decisions often remain split across clients, servers, prompts, approval dialogs, OAuth deployments, and logs. This paper asks whether a runtime can make execution-layer invariants explicit and testable while preserving MCP-like workflows. We define eight invariants: metadata non-authority, grant-backed approval, canonical resources, principal binding, scoped capability invocation, source-and-target data-flow authorization, deny-path audit, and explicit protocol state. We implement these invariants in HCP, a Handle-Capability Protocol reference runtime for MCP-style agent execution that represents calls through principals, resources, grants, capabilities, handles, policy decisions, data-pipe checks, and audit entries. We evaluate HCP against two MCP-like baselines: a naive connection-layer runtime and a practice-informed connection-layer mitigation baseline with metadata linting, session checks, and per-call approvals. Across 10 benchmark cases, the naive baseline permits all modeled attacks, the mitigation baseline permits 6 of 10, and HCP blocks all 10 while preserving audit evidence. Ablations identify which runtime components block attacks and preserve forensic evidence. A local in-memory microbenchmark reports sub-millisecond mean latencies for measured policy, invocation, peek, and pipe operations. A bounded GitHub README-screening sample provides ecosystem signals, not vulnerability findings. The results support a narrow claim: MCP-style agent systems need an execution-control layer in addition to connection-layer conventions.

Ting Liu

SymbolicLight Research Foshan, Guangdong, China

MCP SecurityLLM Agent SecurityAI Agent Security BenchmarksCapability-Based SecurityTool Access Control for LLM AgentsRuntime Verification
AskPDF
Jun 27, 2026

Agent Safety Is Action Alignment

Large language models increasingly act as agents: they call tools, move money, delete records, and send messages on a user's behalf. To keep them safe, practitioners imported the chatbot-era recipe (train the model to refuse unsafe inputs) into the agentic setting, and treat the resulting capability loss as a manageable ``alignment tax.'' We argue this is a category error. Refusal is a primitive for content safety, where the harm is in the model's output and is therefore a learnable function of it. Agentic harm is different in kind: it lies not in any output but in the relation between the authority an action exercises and the authority the user granted, which is absent from the text the model sees. Importing content-safety methods into this regime does not trade capability for safety; it pays capability and buys negative security. We support this with three lines of evidence spanning the autonomy spectrum: defense-trained models learn surface patterns rather than intent; the same training collapses multi-step agents before any threat appears while leaving them exploitable; and even undefended frontier models exceed granted authority under ordinary use. We conclude that action safety cannot be installed in weights. It must be expressed as least privilege, enforced outside the model at the action boundary, and evaluated as action alignment (a relational, deployment-conditioned property) rather than a refusal score.

Shawn Li, Yue Zhao

University of Southern California · Los Angeles, California, USA

Language Model Safety EvaluationAI AlignmentLLM Agent SafetyTool Access Control for LLM Agents
AskPDF
Jun 27, 2026

Capability Gates Are Not Authorization: Confused-Deputy Failures in LLM Agent Frameworks

Tool-using LLM agents increasingly read untrusted content while holding side-effecting tools such as payments, email, CRM, and infrastructure APIs, yet common framework defaults still conflate tool exposure with authorization. We audit whether LangChain/LangGraph, LlamaIndex, and the Stripe Agent Toolkit re-authorize each model-emitted call, with concrete argument values, before execution. Across pinned public-source commits, all three provide capability gating by default, but none provides a deterministic fail-closed per-call value authorization gate by default. We introduce ScopeGate, a five-stage PDP/PEP for agent tool calls: scope, authorization, money ceiling, idempotency, and default deny. Evaluation shows the identical unauthorized payout call executes under LangChain's default dispatch (with a companion LlamaIndex PoC) but is denied by ScopeGate; the tested control reports 0/48 static bypasses, 0/29 unauthorized attempts (40-iteration adaptive run), 0/10 benign false-denies, and Latam-GPT payment-agent containment at 10/10. ASR denotes attempted unauthorized action, containment is not a cure, deployment-tier claims are inference over measured model classes, and no CVE is asserted.

David Mellafe Zuvic

Independent Security Research Chile

AI Agent AuditingLLM AuditingLLM Agent SecurityRuntime Enforcement for AI AgentsTool-Use AuthorizationLLM Agent Safety+1
AskPDF
Jun 27, 2026

Why Trust Your Agent? Empirical Security Gains from TRiSM-Guided Agentic Workflows in Healthcare

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.

Liam Kearns

AuraQ Malvern Worcestershire UK

Medical Report GenerationRAG Poisoning AttacksAgentic WorkflowsLLM Agent SecurityTool Access Control for LLM Agents
AskPDF
Jun 25, 2026

A Deterministic Control Plane for LLM Coding Agents

LLM coding harnesses grant agents broad file and shell access, yet the configuration layer that steers them -- rules files, agent definitions, IDE-specific markdown -- is largely unmanaged. A prevalence study of 10,008 public GitHub repositories (n=6,145 agent config files) finds that agent configurations propagate as undeclared shared components: 10.1% of tracked paths are SHA-256 exact duplicates across independent repositories (fork-adjusted, threshold-independent), with 75.5% of clone pairs crossing organisational boundaries. Two further patterns are indicative: configurations are rarely revised (58% single-commit; 0.4 vs 0.6 commits/month age-normalised against CI/CD workflows), and rarely declare permission boundaries (<1% of agent configs vs 33% of Actions workflows, n=31 true positives). We propose a deterministic control plane above the harness that maps one-to-one to these gaps. Rel(AI)Build treats agent definitions as a managed supply chain (SHA-256 content addressing, HMAC-stamped lockfiles, hash-chained audit logs); enforces tiered permissions and attack-derived blocklists before LLM invocation; gates feature work through a phase state machine with requirement-to-file-to-test traceability; compiles a single canonical definition to seven IDE targets; and detects prompt drift via Jaccard similarity. Conformance tests on injected violations confirm each mechanism enforces its stated invariant; developer outcomes remain future work. Governance of this layer must be deterministic and tool-agnostic -- not delegated to further LLM orchestration.

Padmaraj Madatha

HappiestJuneMinds2026 Technologies (AIP Centre of Excellence)

AI Coding AgentsLLM GuardrailsLLM Agent SecurityAI Agent GovernanceTool Access Control for LLM Agents
AskPDF
Jun 24, 2026

The Unfireable Safety Kernel: Execution-Time AI Alignment for AI Agents and Other Escapable AI Systems

AI agents are granted access to tools, APIs, and other infrastructure, making them active principals in those systems. The dominant approach places controls inside the agent's own runtime: system prompts, output filters, and guardrail libraries. Any control in the agent's address space is reachable by inputs that influence it; this generalizes to any AI system with sufficient reach into its own runtime, a class we term escapable AI systems. We identify four properties that an authorization mechanism must satisfy for architectural control rather than for cooperative requests: process separation, pre-action enforcement on a structurally only path, fail-closed at both the request and system levels, and externalized signed evidence verifiable outside the controlled system's trust boundary. We position this layer as execution-time AI alignment, complementing training-time alignment (RLHF, Constitutional AI) and inference-time alignment. We present the Unfireable Safety Kernel, a Rust reference implementation realizing all four. Its fail-closed invariant is machine-checked at two levels: an SMT theorem (Z3) and an exhaustive bounded-model-checking proof of the production decision function (Kani, 4/4 harnesses). A Python-to-Rust migration was gated on byte-equivalence (1000/1000 fixtures; 17/17 adversarial classes). We evaluate the kernel governing a live, escapable AI system, a deterministic, self-improving world model, against an escape-seeking adversary driving its real self-modification seam: across 1,000 self-modifications, all 704 attempts on the safety-critical core are refused, with no escape; a further 300, under the operator kill switch, are also refused. A separate campaign of 6,240 authorization round-trips had no successful bypass. Against 3 contemporary systems claiming the agent control plane, the agent invokes control; here, it lacks that choice.

Seth Dobrin, Łukasz Chmiel

ARYA Labs PBC

AI AlignmentAI Agent SecurityAI Agent SafetyRuntime Enforcement for AI AgentsTool Access Control for LLM Agents
AskPDF
Jun 22, 2026

Intent-Governed Tool Authorization for AI Agents

AI agents increasingly act through external tools: they read private data, construct structured payloads, submit write requests, export records, and coordinate workflows across application boundaries. Existing authorization mechanisms usually ask whether an integration credential, app, or token can call a tool. That question is necessary but incomplete. A tool call can be authorized by static credentials and still be unjustified by the user's current request. For example, a credential that can read and export records should not expose export authority when the user only asked for a bounded summary, and a model-generated delete call should not execute merely because the integration has a delete scope. This paper proposes Intent-Governed Access Control (IGAC), a server-side authorization layer that treats the user's expressed intent as a monotone, auditable policy attribute for AI-agent tool use. IGAC introduces intent certificates, session-scoped policy narrowing, intent-aware manifest filtering, and intent-tool-payload consistency checks. The central invariant is that user intent may only reduce the authority granted by static integration policy; it never expands scopes, data policy, tenant boundaries, or review requirements. We map IGAC onto OpenPort, an existing governance substrate that already implements authorization-dependent discovery, scope and ABAC-style policy checks, draft-first writes, preflight impact binding, state-witness checks, idempotency, stable reason codes, and audit.

Genliang Zhu, Chu Wang

Accentrust · Georgia Institute of Technology · University of Illinois Urbana-Champaign

AI Agent SecurityAI Agent GovernanceTool-Use AuthorizationAccess ControlTool Access Control for LLM Agents
AskPDF
Jun 20, 2026

Harness-MU: A Safe, Governed, and Effective Harness for Multi-User LLM Agents

The increasing deployment of large language model (LLM) agents in collaborative workflows demands robust multi-user, multi-principal interaction mechanisms capable of enforcing access permissions, resolving authoritative conflicts, and preventing unauthorized data disclosure. However, a fundamental mismatch exists between the single-user training paradigm of contemporary LLMs and the hard constraints required for multi-principal governance, rendering probabilistic, prompt-based safeguards vulnerable under multi-turn adversarial interactions.Our key insight is that governance constraints -- who is authorized, what is restricted, and whose instructions take precedence -- are deterministic runtime variables that should be enforced by execution hooks rather than entrusted to the LLM. We present Harness-MU, the first model-agnostic, zero-tuning infrastructure framework for multi-user LLM agents. By decoupling language generation from safety orchestration, Harness-MU guarantees unbreakable permission boundaries while maximizing compliant demand satisfaction. Across four frontier open-weight and proprietary models on the Muses-Bench benchmark, Harness-MU achieves the goal of privacy preservation across all access-control attacks, outperforming the standard baseline by 0.28--0.39 in utility score and improving instruction-following accuracy by up to 48.9 percentage points. Harness-MU advances the philosophy of Harness Engineering, establishing that systematic infrastructure is essential for solving LLM multi-principal governance challenges. The code and data are available at https://github.com/YuanJrShiuan/Harness-MulUser.

Wangxuan Fan, Xiaoyu Nie, Zhongxiang Dai

The Chinese University of Hong Kong, Shenzhen

Privacy-Preserving Language ModelsLLM Agent SecurityLLM AgentsAI Agent GovernanceTool Access Control for LLM AgentsLLM Agent Harnesses
AskPDF
Jun 18, 2026

When Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents

As LLM agents increasingly select tools autonomously, their choices among tools with different privileges become safety-relevant. However, prior tool-selection studies focus on safety-agnostic metadata preferences, leaving privilege-sensitive choices underexplored. To address this gap, we study over-privileged tool selection, in which an agent selects or escalates to a higher-privilege tool despite a sufficient lower-privilege alternative. We introduce ToolPrivBench to evaluate whether agents choose higher-privilege tools despite sufficient lower-privilege alternatives, measuring both initial selection and escalation after transient tool failures. Across eight domains and five recurring risk patterns, we find that over-privileged tool selection is common among mainstream LLM agents and is further amplified by transient failures. We further find that general safety alignment does not reliably transfer to least-privilege tool choice, while prompt-level controls provide only limited mitigation under transient failures. We therefore introduce a privilege-aware post-training defense that teaches agents to prefer sufficient lower-privilege tools and escalate only when necessary. Our mitigation experiments show that this defense substantially reduces unnecessary high-privilege tool use while preserving general capabilities.

Kaiyue Yang, Yuyan Bu, Jingwei Yi +5

Institute of Information Engineering, Chinese Academy of Sciences · Beijing Academy of Artificial Intelligence · The Chinese University of Hong Kong +2

LLM Agent SecurityAI Agent Security BenchmarksLLM Agent TrainingTool Access Control for LLM Agents
AskPDF
Jun 17, 2026

GateMem: Benchmarking Memory Governance in Multi-Principal Shared-Memory Agents

Memory benchmarks for LLM agents largely assume single-user settings, leaving shared assistants for hospitals, workplaces, campuses, and households understudied. In these deployments, multiple principals write to a common memory pool and query it under different roles, scopes, and relationships, so memory quality requires governance as well as recall. We introduce GateMem, a benchmark for multi-principal shared-memory agents. GateMem jointly evaluates utility for legitimate long-horizon requests with state updates, access control across contextual authorization boundaries, and agent-facing active forgetting after explicit deletion requests. It spans medical, office, education, and household domains, with long-form multi-party episodes, incremental memory injection, hidden checkpoints, structured judging, and leak-target annotations. Across diverse baselines and backbone models, no method simultaneously achieves strong utility, robust access control, and reliable forgetting. Long-context prompting often yields the best governance score at high token cost, while retrieval-based and external-memory methods reduce cost yet still leak unauthorized or deleted information. These results show current memory agents remain far from reliable shared institutional deployment.

Zhe Ren, Yibo Yang, Yimeng Chen +7

School of Artificial Intelligence, Jilin University · 2Shanghai Jiao Tong University · 3King Abdullah University of Science and Technology (KAUST) +2

LLM Agent MemoryAgent Memory GovernanceAI Agent SecurityAI Agent Security BenchmarksMemory Agent BenchmarksAI Agent Governance+3
AskPDF
Jun 8, 2026

SecureClaw: Clawing Back Control of LLM Agents

Tool-using large language model (LLM) agents face two distinct security failures: unauthorized external actions and exposure of sensitive plaintext inside the runtime before any final output check can intervene. Existing defenses usually protect one boundary, either the planner/runtime or the point where external actions are executed, and therefore do not by themselves secure both surfaces. We present SecureClaw, a dual-boundary architecture that enforces authorization in a trusted executor and keeps raw protected data outside the LLM runtime. Sensitive reads pass through a trusted gateway that replaces raw values with reference IDs. In the evaluated deployment, the gateway also provides short planning summaries that deliberately release selected information, a process called declassification. Writes that change external state follow a PREVIEW→\rightarrowCOMMIT protocol in which only a trusted executor may execute the exact request authorized by policy. The runtime can still plan over summaries and reference IDs, but cannot directly resolve the IDs into secrets or perform side effects. Across the AgentDojo, AgentLeak, and Agent Security Bench (ASB) benchmarks, SecureClaw is the only defense we evaluate in a common harness that simultaneously retains usable task utility and achieves 0% attack success rate (ASR) on ASB, 0.64% ASR on AgentDojo, and 3.23% overall leak on AgentLeak's attacked parity lane, which measures final-output and internal-relay leakage. Code is available at https://github.com/ponyyuhan/SecureClaw.

Yuhan Ma, Stefan Schmid

TU Berlin

Data LeakageLLM Agent SecurityPrivacy Leakage in Language ModelsTool Access Control for LLM AgentsPrivacy Protection for LLM Agents
AskPDF
Jun 7, 2026

AgentTrust: A Self-Improving Trust Layer for AI-Agent Actions

AI agents increasingly take consequential actions -- shell commands, cloud operations, and arbitrary tool-calls -- so a trust layer must decide, per action, whether to allow, warn, block, or escalate. We argue that the right way to reason about such a layer is by threat type. Lexical (fixed-signature) threats, where danger lives in a stable token, are decidable by deterministic rules; semantic (intent-dependent) threats, where a benign and a malicious action share the same surface, are out of reach for rules by construction. We make this concrete with a negative proof: a determined, hand-authored cloud rule pack lifts held-out accuracy only 48 to 56% overall and moves the semantic categories by 0pp (data_db 29 to 29, observability 59 to 59, supply_chain 50 to 50), while a strong LLM judge carries exactly those categories. We give the judge a self-learning capability: on a corpus that is mainly semantic attacks it nearly doubles rule accuracy (48% to 83.6-85.2%) with near-zero false-blocks, and this holds across two model providers. We turn this into a self-improving dual-store system: the judge distills a growing deterministic rule floor on lexical threats (cheaper over time) and feeds a guarded RAG memory on semantic threats (a verdict-cache fails -- surface-twins collapse to ~58% -- so a corroboration guard lifts semantic accuracy +13pp, 70 to 84). The result is what sets AgentTrust v2 apart from its static v1 predecessor: a trust layer that self-evolves from its own stream of decisions -- cheaper on the lexical class (it distils its own rules) and smarter on the semantic class (it accrues guarded precedent), while never hard-blocking a benign action. An end-to-end online replay shows the judge-call rate falling (50% to 44%) and judge-domain accuracy rising (71% to 80%), with 0 benign hard-blocks across 45,000 actions.

Chenglin Yang

Independent Researcher

AI Agent ReliabilityLLM-as-a-JudgeAI Agent SecurityLLM Agent SecurityRuntime Enforcement for AI AgentsTool-Use Authorization+2
AskPDF
Jun 4, 2026

Will the Agent Recuse Itself? Measuring LLM-Agent Compliance with In-Band Access-Deny Signals

As autonomous LLM agents increasingly hold real credentials and operate infrastructure without a human in the loop, operators have no standard way to tell an agent that a resource is off-limits. Access controls either let the agent in (it has valid credentials) or hard-fail it (indistinguishable from any other client). We propose a third mode: a lightweight, published in-band deny signal -- the Recuse Signal -- that a server emits over a protocol's existing channels (an SSH banner, a PostgreSQL NOTICE) asking a connecting automated agent to voluntarily withdraw. This is a cooperative governance control, the robots.txt analogue for live access; it is explicitly not a security boundary. Its value is entirely empirical and, to our knowledge, unmeasured: do compliant LLM agents actually honor such a signal? We define the signal as an open mini-standard, implement three zero- or low-footprint adapters (an SSH banner/PAM hook, a PostgreSQL wire-protocol proxy, and a Kubernetes admission webhook), deploy them on a live production host, and run a controlled experiment in which fresh agents are given a benign operations task and observed for recusal. In a pilot (SSH; OpenAI GPT-4o and GPT-4o-mini; and Claude Code as a deployed agent), the signal cleanly induces recusal -- 100% recusal when present versus 100% task completion in a no-signal control -- and, revealingly, behaves as a cooperative rather than absolute signal: an explicit operator-authorization framing flips the most capable model to proceed, while other agents continue to defer to the on-host policy. We release the standard, adapters, and experiment harness for reproduction.

Thamilvendhan Munirathinam

LLM Agent EvaluationLLM Refusal BehaviorAI Agent GovernanceTool Access Control for LLM Agents
AskPDF
Jun 2, 2026

Agent libOS: A Runtime Substrate for Capability-Controlled Self-Evolving LLM Agents

Large language model (LLM) agents are becoming long-running software actors rather than fixed tool users. They accumulate memory, activate skills, synthesize tools, fork children, attach remote resources, and commit checkpoints into reusable execution images. These mechanisms improve adaptability, but also create a systems-security failure mode: if exposing an action also grants the authority needed to perform it, self-evolution becomes a permission-escalation path. This paper presents Agent libOS, an agent-native library-OS substrate for capability-controlled self-evolving agents. Its central invariant is that model-visible affordances may evolve while resource authority changes only through explicit, audited runtime primitives. Agent libOS represents an agent as an AgentProcess with process identity, process-local Object Memory, message queues, a tool table, loaded Skills, process-local Deno/TypeScript JIT tools, child processes, budgets, checkpoints, and explicit capabilities. AgentImage objects define boot-time prompt and tool-table state; Skills and JIT tools extend the action surface; checkpoint-derived images make internal state reusable. None of these mechanisms grants filesystem, shell, human, memory, process, checkpoint, image, JSON-RPC, MCP, or PTY authority by itself. The prototype implements process-local namespaces, persistent runtime state, LLM-call observability, human approval queues, budgets, syscall-mediated JIT tools, trusted Runtime Modules, Object-bound PTY sessions, checkpoint restore/fork/commit, JSON-RPC and MCP providers, and a deterministic runtime-safety benchmark. On 27 versioned deterministic tasks, it completed the task plans while preventing all modeled unauthorized side effects, with a 7.0% conservative false-denial rate. Simple wrapper and sandbox baselines preserved task completion but failed most safety checks.

Yingqi Zhang

Department of Computer Science and Technology, Tsinghua University Beijing, China

AI Agent SecurityLLM AgentsCapability-Based SecurityTool Access Control for LLM AgentsSelf-Evolving Agents
AskPDF
Jun 2, 2026

Overlaying Governance: A Compositional Authorization Framework for Delegation and Scope in Agentic AI

As AI systems evolve from passive models into autonomous active agents capable of initiating actions, collaborating, and delegating tasks, the traditional boundaries of software systems blur. Traditional authorization and delegation frameworks, built around fixed principals, explicit requests, and static scopes, are insufficient to govern agentic systems. Agentic AI demands richer authorization semantics: agents must inherit and delegate permissions, act under time-limited authority, and coordinate through shared protocols. Existing Identity and Access Management (IAM) systems fail to fully capture this notion of agency, lacking mechanisms for recursive delegation, contextual boundaries, and dynamic scoping as executable governance primitives. Unlike access delegation standards such as OAuth 2.0, we treat delegation as a contractual term rather than merely a static token-based consent credential. This paper proposes a compositional governance framework that introduces primitives indispensable for agentic AI. We define types of delegation and their permissions and accountability implications, and we introduce a notion of resource scope attenuation to bound agentic access envelopes. These concepts are expressed as general relational definitions that can be composed into existing authorization domains (e.g., financial systems). To operationalize this composition, we define a compositional operator that overlays new agentic semantics, such as recursive delegation chains, onto existing relational policies without rewriting them. We substantiate this framework through formal proofs and empirical evaluation, showing that it provides a formal yet practical foundation for accountable authorization in agentic AI systems.

Amjad Ibrahim, Yong Li

Huawei Heisenberg Research Center Germany

AI AccountabilityAI Agent SecurityAI Agent GovernanceAccess ControlTool Access Control for LLM AgentsAgentic AI
AskPDF
Jun 2, 2026

ToolGate: Token-Efficient Pre-Call Control for Tool-Augmented Vision-Language Agents

Tool-augmented vision-language agents can acquire external perceptual evidence through OCR, detection, segmentation, and other tools, but executing every proposed tool call is costly and sometimes unnecessary. We study the pre-call control problem: after a ReAct-style VLM agent proposes a perceptual tool call, should the call be executed, or skipped before its output enters the context? Across five benchmarks, we find that the baseline agent exhibits poor local selectivity: helpful and harmful calls occur at similar rates (11.8% vs. 9.9%), while most calls do not change the immediate forced-answer prediction. We introduce ToolGate, a lightweight external controller that predicts execute/skip decisions from trajectory text and simple structural features. Across two Qwen3-VL backbones, ToolGate reduces token cost to 64-69% of the unrestricted ReAct baseline while preserving average accuracy in cross-domain settings. With matched-domain trajectory training on Qwen3-VL-30B, it further improves average accuracy by 1.65 points. These results show that tool-augmented VLM agents benefit not only from better perceptual tools, but also from explicit control over when tool outputs are worth paying for.

Anjie Liu, Yan Song, Zhixun Chen +3

The Hong Kong University of Science and Technology (Guangzhou) · University College London · AI Lab, The Yangtze River Delta

Tool Use in VLMsTool-Augmented Language Model AgentsEfficient VLM InferenceTool-Using Vision-Language AgentsTool Access Control for LLM Agents
AskPDF
Jun 1, 2026

AgentRedBench: Dynamic Redteaming and Integration-Aware Defense for LLM Agents over SaaS Integrations

Indirect prompt injection in tool-use agents is a concrete production threat: LLM agents read from integrations (third-party services such as Gmail, Salesforce, or Jira accessed through tool calls) whose response content the user neither writes nor controls. Existing benchmarks under-measure the threat: most cover only a handful of integrations with the same attack payload replayed across runs, and open-source guards are trained on chat-style data rather than tool-response content. We introduce AGENTREDBENCH, a dynamic LLM-driven redteaming benchmark of 215 subtle underspecified authorization (attacks at the boundary of what the user's request authorises) scenarios across 24 enterprise integrations in nine functional families and five attack types. Across an eight-model panel (Anthropic, OpenAI, Google), no-guard ASR (attack success rate) ranges from 32% (Claude Sonnet 4.6) to 81% (Gemini 3 Flash). To keep the scenario set out of training corpora and preserve headline ASR meaning over time, we release the codebase, integration schemas, and AGENTREDGUARD model openly; the canonical scenarios are evaluated through a maintainer-mediated channel with immutable versioning. We release AGENTREDGUARD alongside the benchmark: a guard trained on an integration-diverse corpus of adversarial tool-response content. AGENTREDGUARD cuts panel ASR from 69.9% to 2.4% at 0.37% false-positive rate, outperforming every open-source baseline with non-trivial detection (Llama Guard, PromptGuard 2, ProtectAI) on both axes. Cross-integration and cross-attack type holdouts both confirm the gain transfers beyond the training subset.

Hiskias Dingeto, William Leeney

StackOne Technologies

LLM Red TeamingLLM Agent SecurityAI Agent Security BenchmarksIndirect Prompt InjectionPrompt Injection DefensePrompt Injection Attacks on LLMs+4
AskPDF
May 27, 2026

AIRGuard: Guarding Agent Actions with Runtime Authority Control

Tool-using language agents turn model decisions into external side effects: they read files, run scripts, call APIs, send messages, and invoke Model Context Protocol tools. This makes agent attacks different from jailbreaks. The harmful step is often not an obviously forbidden output, but an ordinary executable action that becomes unsafe because attacker-controlled context steers authorized access against the user's interest. We identify this failure mode as authority confusion: untrusted resources may inform reasoning, but they must not authorize side effects. We present AIRGuard, a runtime guard that operationalizes least privilege as action-time authorization. AIRGuard normalizes heterogeneous tool calls, derives task authority into step-level authority, tracks source and target trust, simulates sensitive side effects, audits cross-step risk, and enforces decisions before actions execute. On AgentTrap, AIRGuard reduces Sonnet 4.6 attack success from 36.3% without defense to 5.5%. On DTAP-150, AIRGuard preserves 76.0% benign utility with Haiku 4.5, compared with 52.0% for ARGUS and 42.0% for MELON. An ablation further shows that prompt-only policy helps only modestly, whereas a dedicated runtime authority-control layer gives the agent system direct control over tool-mediated side effects. Code and data are available at https://github.com/Sophie508/AIRGuard.

Suliu Qin, Haomin Zhuang, Yujun Zhou +2

University of Liverpool · University of Notre Dame · 2Inria, France

AI Agent SecurityTool-Using AgentsTool Access Control for LLM Agents
AskPDF
May 26, 2026

FinHarness: An Inline Lifecycle Safety Harness for Finance LLM Agents

Finance LLM agents must simultaneously block prompt-induced unauthorized actions and approve legitimate multi-step business workflows. However, boundary filters often miss irreversible mid-trajectory tool calls, while post-hoc LLM judges perform auditing only after termination -- too late for intervention and at a computational cost that scales linearly with trace length. We present FinHarness, an inline safety harness that wraps a finance agent end-to-end with three components: a Query Monitor that fuses single-turn intent with cross-turn drift, a Tool Monitor that evaluates each prospective tool call, and a Cascade module that integrates per-step risk and adaptively routes verification between a lightweight and an advanced-tier LLM judge. Fired risk factors are re-injected into the agent input as ex-ante evidence, enabling the agent to refuse, re-plan, or approve on its own. On FinVault, routed FinHarness cuts ASR from 38.3% to 15.0% while largely preserving benign approval (41.1%→39.3%41.1\% \to 39.3\%), and uses 4.7×4.7\times fewer advanced-judge calls than an always-advanced ablation.

Haoxuan Jia, Yang Liu, Bin Chong +10

Nanyang Technological University · Tsinghua University · Peking University +8

AI Agent ReliabilityLLM GuardrailsLLM Agent VerificationAI Agent MonitoringSafety FilteringRuntime Enforcement for AI Agents+4
AskPDF
May 18, 2026

Overeager Coding Agents: Measuring Out-of-Scope Actions on Benign Tasks

Coding agents now run autonomously with shell, file, and network privileges. When a user issues a benign request, the agent sometimes does more than asked: it deletes unrelated files, wipes a stale credentials backup, or rewrites configuration the user never mentioned. We call these scope expansions overeager actions, an authorization problem distinct from capability failures, prompt injection, or sandbox escapes. We present OverEager-Gen, a benchmark dedicated to overeager behavior on benign tasks. Building it surfaces a measurement-validity issue: if a benchmark spells out the authorized scope inside the prompt, the agent stops inferring boundaries and starts pattern-matching declaration text. On Claude Code, stripping the consent declaration alone raises the overeager rate from 0.0% to 17.1% on paired scenarios (McNemar exact p = 2.4 x 10^-4). OverEager-Gen therefore certifies each scenario's discriminative power before admission via a behavioral-gradient validator, audits internal tool calls through a dual-channel stack (PATH-injected shim plus per-agent event streams), and ships byte-identical consent_kept and consent_stripped variants. OverEager-Bench contains 500 validated scenarios and ~7,500 runs across four agent products (Claude Code, OpenHands, Codex CLI, Gemini CLI) and six base models; a 50-sample re-annotation gives Cohen's kappa = 0.73 and rule-judge recall = 1.00. Stripping consent multiplies the overeager rate on every shared base model (Delta in [11.9, 17.2] pp). The framework axis dominates effect size: a permissive cluster (Claude Code, Codex CLI, Gemini CLI) runs at 5.4-27.7% while the ask-to-continue framework (OpenHands) sits at 0.2-4.5% (Fisher p <= 10^-5). Within-framework base-model variance reaches 15.9 pp, indicating that model-layer alignment does not fully propagate through permissive permission gating.

Yubin Qu, Ying Zhang, Yanjun Zhang +4

Griffith University · Wake Forest University · Nanyang Technological University +2

Tool Access Control for LLM AgentsComputer-Use Agent BenchmarksCoding AgentsAI Agent EvaluationAI Agent SecurityAI Agent Security Benchmarks+3
AskPDF
May 18, 2026

Prompts Don't Protect: Architectural Enforcement via MCP Proxy for LLM Tool Access Control

Large language models increasingly operate as autonomous agents that select and invoke tools from large registries. We identify a critical gap: when unauthorized tools are visible in an agent's context, models select them in adversarial scenarios -- even when explicitly instructed otherwise. We propose a governed MCP proxy that enforces attribute-based access control (ABAC) at two points: tool discovery, where unauthorized tools are removed from the model's context window, and tool invocation, where a second check blocks any unauthorized call. Across three models (Qwen 2.5 7B, Llama 3.1 8B, Claude Haiku 3.5) and 150 adversarial tasks spanning four attack categories, our proxy reduces unauthorized invocation rate (UIR) to 0% while adding under 50ms median latency. Prompt-based restrictions reduce UIR by only 11--18 percentage points, leaving substantial residual risk. Our results show that architectural enforcement -- not prompting -- is necessary for reliable tool access control in deployed agentic systems.

Rohith Uppala

Independent Researcher

LLM Agent SecurityAI ControlLLM Tool UseAccess ControlTool Access Control for LLM Agents
AskPDF
May 14, 2026

Do Coding Agents Understand Least-Privilege Authorization?

As coding agents gain access to shells, repositories, and user files, least-privilege authorization becomes a prerequisite for safe deployment: an agent should receive enough authority to complete the task, without unnecessary authority that exposes sensitive surfaces. To study whether current models can infer this boundary themselves, we first introduce permission-boundary inference, where a model maps a task instruction and terminal environment to a file-level read/write/execute policy, and AuthBench, a benchmark of 120 realistic terminal tasks with human-reviewed permission labels and executable validators for utility and attack outcomes. AuthBench shows that authorization is not a simple conservative-versus-permissive calibration problem: frontier models often omit permissions required by the execution chain while also granting unused or sensitive accesses. Increasing inference-time reasoning does not resolve this mismatch. Instead, each model moves toward a model-specific authorization attractor: more reasoning makes it more consistent in its own failure mode, whether broad-but-exposed or tight-but-brittle. This suggests that direct policy generation is the bottleneck, because a single generation must both discover all necessary accesses and reject all unnecessary ones. We therefore propose Sufficiency-Tightness Decomposition, which first generates a coverage-oriented policy by forward-simulating the task and then audits each granted entry for grounding and sensitivity. Across tested models, this decomposition improves sensitive-task success by up to 15.8% on tightness-biased models while reducing attack success across all evaluated models.

Zheng Yan, Jingxiang Weng, Charles Chen +9

Evolvent AI Research Team

Software Engineering AgentsAI Agent SecurityAI Agent Security BenchmarksAccess ControlTool Access Control for LLM Agents
AskPDF
May 12, 2026

Options, Not Clicks: Lattice Refinement for Consent-Driven MCP Authorization

As Model Context Protocol adoption grows, securing tool invocations via meaningful user consent has become a critical challenge, as existing methods, broad always allow toggles or opaque LLM-based decisions, fail to account for dangerous call arguments and often lead to consent fatigue. In this work, we present Conleash, a client-side middleware that enforces boundary-scoped authorization by utilizing a risk lattice to auto-permit safe calls within known boundaries while escalating risks, a policy engine for user-defined invariants, and a refinement loop that converts user decisions into reusable rules. Evaluated on 984 real-world traces, Conleash achieved 98.2% accuracy, caught 99.4% of escalations, and added only 8.2 ms of overhead for policy verification; furthermore, in a user study where N=16, participants significantly preferred Conleash scoped permissions over traditional methods, citing higher trust and reduced prompting.

Ying Li, Yanju Chen, Peiran Wang +4

University of California, Los Angeles USA · University of California, San Diego USA · University of Texas at Arlington USA +1

MCP SecurityTool-Use AuthorizationAccess ControlTool Access Control for LLM Agents
AskPDF
May 11, 2026

The Granularity Mismatch in Agent Security: Argument-Level Provenance Solves Enforcement and Isolates the LLM Reasoning Bottleneck

Tool-using LLM agents must act on untrusted webpages, emails, files, and API outputs while issuing privileged tool calls. Existing defenses often mediate trust at the granularity of an entire tool invocation, forcing a brittle choice in mixed-trust workflows: allow external content to influence a call and risk hijacked destinations or commands, or quarantine the call and block benign retrieval-then-act behavior. The key observation behind this paper is that indirect prompt injection becomes dangerous not when untrusted content appears in context, but when it determines an authority-bearing argument. We present PACT (Provenance-Aware Capability Contracts), a runtime monitor that assigns semantic roles to tool arguments, tracks value provenance across replanning steps, and checks whether each argument's origin satisfies its role-specific trust contract. Under oracle provenance, PACT achieves 100% utility and 100% security on mixed-trust diagnostic suites, while flat invocation-level monitors incur false positives or false negatives. In full AgentDojo deployments across five models, PACT reaches 100% security on the three strongest models while recovering 38.1--46.4% utility, 8--16 percentage points above CaMeL at the same security level. Ablations show that both semantic roles and cross-step provenance are necessary. PACT reframes agent security as authority binding, and isolates the remaining deployment bottleneck to provenance inference and contract synthesis.

Linfeng Fan, Ziwei Li, Yuan Tian +3

Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China · King Abdullah University of Science and Technology, Thuwal, Saudi Arabia · Dongbei University of Finance and Economics, Dalian, China +1

LLM Agent SecurityInformation Flow ControlPrompt Injection DefenseAccess ControlTool Access Control for LLM Agents
AskPDF
May 9, 2026

FORTIS: Benchmarking Over-Privilege in Agent Skills

Large language model agents increasingly operate through an intermediate skill layer that mediates between user intent and concrete task execution. This layer is widely treated as an organizational abstraction, but we argue it is also a privilege boundary that current models routinely exceed. We present FORTIS, a benchmark that evaluates over-privilege in agent skills across two stages: whether a model selects the minimally sufficient skill from a large overlapping library, and whether it executes that skill without expanding into broader tools or actions than the skill permits. Across ten frontier models and three domains, we find that over-privileged behavior is the norm rather than the exception. Models consistently reach for higher-privilege skills and tools than the task requires, failing at both stages at rates that remain high even for the strongest available models. Failure is especially severe under the ordinary conditions of real user interaction: incomplete specification, convenience framing, and proximity to skill boundaries. None of these requires adversarial construction. The results indicate that the skill layer, far from containing agent behavior, is itself a primary source of privilege escalation in current systems.

Shawn Li, Chenxiao Yu, Han Wang +8

University of Southern California · University of Illinois at Urbana-Champaign · 3Adobe Research +3

LLM Agent SecurityAI Agent Security BenchmarksAI Agent Safety BenchmarksTool Access Control for LLM AgentsAgentic AI
AskPDF
May 8, 2026

TeamBench: Evaluating Agent Coordination under Enforced Role Separation

Agent systems often decompose a task across multiple roles, but these roles are typically specified by prompts rather than enforced by access controls. Without enforcement, a team pass rate can mask whether agents actually coordinated or whether one role effectively did another role's work. We present TeamBench, a benchmark with 851 task templates and 931 seeded instances for evaluating agent coordination under operating system-enforced role separation. TeamBench separates specification access, workspace editing, and final certification across Planner, Executor, and Verifier roles, so that no role can read the full requirements, modify the workspace, and certify the final answer. Prompt-only and sandbox-enforced teams reach statistically indistinguishable pass rates, but prompt-only runs produce 3.6 times more cases where the verifier attempts to edit the executor's code. Verifiers approve 49% of submissions that fail the deterministic grader, and removing the verifier improves mean partial score in the ablation. Team value is also conditional. Teams benefit when single agents struggle, but hurt when single agents already perform well. A 40-session human study under the same role separation shows that our benchmark exposes interaction patterns that pass rate misses. Solo participants work through the task directly, human participants paired with agents often collapse into quick approval, and human teams spend more effort coordinating missing information across roles.

Yubin Kim, Chanwoo Park, Taehan Kim +9

MIT · Google Research · Independent Researcher +1

Multi-Agent CoordinationLLM Agent EvaluationAI Agent SecurityAI Agent BenchmarksTask DecompositionTool Access Control for LLM Agents+1
AskPDF