Auditing Agent Harness Safety

• URL: http://arxiv.org/abs/2605.14271v2
• Date: Sat, 16 May 2026 00:50:55 GMT
• Title: Auditing Agent Harness Safety
• Abstract summary: LLM agents increasingly run inside execution harnesses that dispatch tools, allocate resources, and route messages between specialized components.<n>Most safety benchmarks score only final outputs or terminal states, even though many violations occur mid-trajectory rather than at termination.<n>We propose HarnessAudit, a framework that audits full execution trajectories across boundary compliance, execution fidelity, and system stability.
• Score: 81.22315979618612
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LLM agents increasingly run inside execution harnesses that dispatch tools, allocate resources, and route messages between specialized components. However, a harness can return a correct, benign answer over a trajectory that accesses unauthorized resources or leaks context to the wrong agent. Output-level evaluation cannot see these failures, yet most safety benchmarks score only final outputs or terminal states, even though many violations occur mid-trajectory rather than at termination. The central question is whether the harness respects user intent, permission boundaries, and information-flow constraints throughout execution. To address this gap, we propose HarnessAudit, a framework that audits full execution trajectories across boundary compliance, execution fidelity, and system stability, with a focus on multi-agent harnesses where these risks are most pronounced. We further introduce HarnessAudit-Bench, a benchmark of 210 tasks across eight real-world domains, instantiated in both single-agent and multi-agent configurations with embedded safety constraints. Evaluating ten harness configurations across frontier models and three multi-agent frameworks, we find that: (i) task completion is misaligned with safe execution, and violations accumulate with trajectory length; (ii) safety risks vary across domains, task types, and agent roles; (iii) most violations concentrate in resource access and inter-agent information transfer; and (iv) multi-agent collaboration expands the safety risk surface, while harness design sets the upper bound of safe deployment.

Related papers

• Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification [32.337075755765056]
  Vera is an endto-end automated safety testing framework that instantiates software engineering testing principles for non-deterministic agents.<n>We release Vera, comprising 1600 executable safety cases spanning 124 risk categories across execution settings.<n>These results indicate that modular, executable testing infrastructure is essential for rigorous and maintainable safety evaluation of rapidly evolving agentic systems.
  arXiv  Detail & Related papers  (2026-07-02T07:08:26Z)
• AgentLens: Interpretable Safety Steering via Mechanistic Subspaces for Multi-Turn Coding Agent [53.82005364479556]
  Coding agents based on large language models (LLMs) demonstrate remarkable autonomous capabilities.<n>Existing safety mechanisms mainly rely on external guardrails.<n>We propose AgentLens, a white-box defense framework that performs runtime safety detection and representation-level mitigation.
  arXiv  Detail & Related papers  (2026-06-21T21:13:55Z)
• AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments [32.982317538632806]
  We propose AgentCanary, a comprehensive security evaluation framework for autonomous AI agents.<n>AgentCanary provides a systematic solution along three contributions.<n>We evaluate a broad set of frontier models on AgentCanary against multiple established adversarial attack methods.
  arXiv  Detail & Related papers  (2026-06-09T06:55:37Z)
• From Risk Classification to Action Plan Remediation: A Guardrail Feedback Driven Framework for LLM Agents [35.39244077703096]
  Guardrails typically safeguard agents by evaluating proposed actions or inputs before execution.<n>Existing guardrails often flag the entire task uniformly as unsafe, thereby blocking the threat but sacrificing the benign part.<n>We introduce TRIAD, a guardrail-integrated agent framework that leverages guardrail-generated verbal feedback as a guiding signal to keep the agent aligned with benign objectives.
  arXiv  Detail & Related papers  (2026-06-04T07:34:35Z)
• Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security [57.35851886874902]
  Agentic AI systems execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that challenge trustworthiness.<n>This survey provides a focused examination of trustworthy agentic AI through two core dimensions that are critical for high-risk deployments.<n>For each dimension, we clarify key concepts, identify where risks emerge along the agent workflow, and summarize stage-targeted mitigation strategies.
  arXiv  Detail & Related papers  (2026-05-17T10:26:37Z)
• On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment [54.30690671490447]
  Existing safety-alignment signals are largely response-level or off-policy.<n>FATE transforms verifier-scored failures into repair supervision without expert demonstrations.<n>FATE reduces attack success rate by 33.5%, harmful compliance by 82.6%, and improves external trajectory-safety diagnosis by 6.5%.
  arXiv  Detail & Related papers  (2026-05-12T09:56:28Z)
• Safe Bilevel Delegation (SBD): A Formal Framework for Runtime Delegation Safety in Multi-Agent Systems [4.161562398794914]
  We propose a formal framework for runtime delegation safety in hierarchical multi-agent systems.<n>We instantiate Safe Bilevel Delegation (SBD) in three high-stakes domains--medical AI (MIMIC-III), financial risk control (S and P 500), and educational agent supervision (ASSISTments)
  arXiv  Detail & Related papers  (2026-04-30T03:15:05Z)
• AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security [126.49733412191416]
  Current guardrail models lack agentic risk awareness and transparency in risk diagnosis.<n>We propose a unified three-dimensional taxonomy that categorizes agentic risks by their source (where), failure mode (how), and consequence (what)<n>We introduce a new fine-grained agentic safety benchmark (ATBench) and a Diagnostic Guardrail framework for agent safety and security (AgentDoG)
  arXiv  Detail & Related papers  (2026-01-26T13:45:41Z)
• Building a Foundational Guardrail for General Agentic Systems via Synthetic Data [76.18834864749606]
  LLM agents can plan multi-step tasks, intervening at the planning stage-before any action is executed-is often the safest way to prevent harm.<n>Existing guardrails mostly operate post-execution, which is difficult to scale and leaves little room for controllable supervision at the plan level.<n>We introduce AuraGen, a controllable engine that synthesizes benign trajectories, injects category-labeled risks with difficulty, and filters outputs via an automated reward model.
  arXiv  Detail & Related papers  (2025-10-10T18:42:32Z)
• AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning [78.5751183537704]
  AdvEvo-MARL is a co-evolutionary multi-agent reinforcement learning framework that internalizes safety into task agents.<n>Rather than relying on external guards, AdvEvo-MARL jointly optimize attackers and defenders.
  arXiv  Detail & Related papers  (2025-10-02T02:06:30Z)
• SafeMind: Benchmarking and Mitigating Safety Risks in Embodied LLM Agents [7.975014390527644]
  Embodied agents powered by large language models (LLMs) inherit advanced planning capabilities; however, their direct interaction with the physical world exposes them to safety vulnerabilities.<n>We present SafeMindBench, a multimodal benchmark with 5,558 samples spanning four task categories (Instr-Risk, Env-Risk, Order-Fix, Req-Align) across high-risk scenarios such as sabotage, harm, privacy, and illegal behavior.<n>We introduce SafeMindAgent, a modular Planner-Executor architecture integrated with three cascaded safety modules, which incorporate safety constraints into the reasoning process.
  arXiv  Detail & Related papers  (2025-09-30T07:24:04Z)
• Seven Security Challenges That Must be Solved in Cross-domain Multi-agent LLM Systems [16.838103835766066]
  Large language models (LLMs) are rapidly evolving into autonomous agents that cooperate across organizational boundaries.<n>This position paper maps the security agenda for cross-domain multi-agent LLM systems.
  arXiv  Detail & Related papers  (2025-05-28T18:19:03Z)
• SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents [58.65256663334316]
  We present SafeAgentBench -- the first benchmark for safety-aware task planning of embodied LLM agents in interactive simulation environments.<n>SafeAgentBench includes: (1) an executable, diverse, and high-quality dataset of 750 tasks, rigorously curated to cover 10 potential hazards and 3 task types; (2) SafeAgentEnv, a universal embodied environment with a low-level controller, supporting multi-agent execution with 17 high-level actions for 9 state-of-the-art baselines; and (3) reliable evaluation methods from both execution and semantic perspectives.
  arXiv  Detail & Related papers  (2024-12-17T18:55:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.