HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety

• URL: http://arxiv.org/abs/2608.17597v1
• Date: Tue, 18 Aug 2026 10:03:58 GMT
• Title: HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety
• Abstract summary: We present a lifecycle oriented benchmark that organizes agent safety into six operational phases.<n>We evaluate each trajectory using Utility, Attack Success Rate, Persistence, and Detection.<n>We find that explicit risk recognition does not reliably lead to safe action, as some configurations detect risks in more than 90% of runs.
• Score: 45.163264704448125
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models are increasingly deployed through agent harnesses that manage tools, extensions, persistent state, permissions, and external actions. Existing safety benchmarks mainly target individual attack mechanisms or a limited subset of operational settings, making it difficult to compare how safety failures emerge across different harness responsibilities. We present HarnessRisk, a lifecycle oriented benchmark that organizes agent harness safety into six operational phases including Harness Configuration, Capability Extension, Runtime Operation, State Persistence, Action Control, and Incident Recovery. HarnessRisk contains 128 sandboxed cases, each pairing a benign user objective with an adversarial instruction embedded in an untrusted workflow artifact. We evaluate each trajectory using Utility, Attack Success Rate, Persistence, and Detection. Across three harnesses, six language models, and 14 model and harness configurations, attack success ranges from 12.6% to 80.9%, while Utility remains between 75.0% and 97.6%. Harness Configuration is the most vulnerable phase across all three harnesses, showing that attacks can succeed by altering security sensitive parameters within otherwise authorized workflows. We also find that explicit risk recognition does not reliably lead to safe action, as some configurations detect risks in more than 90% of runs while retaining substantial attack success. These results highlight the need to evaluate agent safety across multiple harness responsibilities and at the level of the deployed model and harness configuration.

Related papers

• EvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents [74.54929751174289]
  EvoSafeHarness is a safety-specific optimization framework that synthesizes a deployable harness for a frozen model in a target domain.<n>It reduces average attack success rate from 45.6% to 10.0% at a 3.3-point utility cost.<n>It also achieves the best score on Agent-SafetyBench for every victim.
  arXiv  Detail & Related papers  (2026-09-05T05:56:41Z)
• StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing [80.39644823192113]
  We propose StepGuard, a step-level guard model that can audit completed agent trajectories and check tool actions before they are executed.<n>StepGuard achieves the highest average accuracy among open-weight guard models, with performance comparable to GPT-5.4.<n>When used to guard agents on AgentDojo and AgentDyn, StepGuard reduces mean attack success rate by 77.3%.
  arXiv  Detail & Related papers  (2026-08-25T16:17:27Z)
• ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents [23.994328225666663]
  Cowork agents may complete benign tasks while disclosing protected data, manipulating unauthorized state, invocate unauthorized API.<n>We define behavioral safety and introduce ActBench, a benchmark that evaluates such behavior risk from execution trajectories rather than final responses.<n>ActBench contains 600 cases from 213 scenarios, spanning 15 risk behaviors, six execution spaces, and 48 web-service APIs.
  arXiv  Detail & Related papers  (2026-08-10T11:45:03Z)
• HarnessSafe: Evaluating Safety Across Persistent Carriers in Agent Harnesses [20.04545361404688]
  harnesses persist state across tasks and sessions through persistent carriers like memory, skills, tools, and shared artifacts.<n>This capability creates delayed safety risks: attacker-influenced content can cross system boundaries and later affect the execution of a benign request.<n>We present HarnessSafe, a benchmark comprising 328 executable cases across seven persistent-carrier families and evaluated on most mainstream agent harnesses.
  arXiv  Detail & Related papers  (2026-08-07T09:03:49Z)
• AgentS4D: Benchmarking Runtime Risks across the Execution Lifecycle of LLM-Based Workspace Agents [10.99961131065026]
  Large language model (LLM)-based workspace agents execute stateful, multi-step across heterogeneous resources.<n>Recent benchmarks have advanced executable safety testing and trajectory-aware verification.<n>We introduce AgentS4D, a sandboxed benchmark for lifecycle-wide runtime safety evaluation.
  arXiv  Detail & Related papers  (2026-07-29T15:55:45Z)
• Auditing Agent Harness Safety [81.22315979618612]
  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.
  arXiv  Detail & Related papers  (2026-05-14T02:14:28Z)
• 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)
• SafeHarness: Lifecycle-Integrated Security Architecture for LLM-based Agent Deployment [19.947119280467934]
  safeharness is a security architecture in which four proposed defense layers are woven directly into the agent lifecycle.<n>We evaluate safeharness on benchmark datasets across diverse harness configurations.
  arXiv  Detail & Related papers  (2026-04-15T08:59:00Z)
• ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis [96.92417622318267]
  ATBench is a trajectory-level benchmark for structured, diverse, and realistic evaluation of agent safety.<n>It organizes agentic risk along three dimensions: risk source, failure mode, and real-world harm.<n>It contains 1,000 trajectories (503 safe and 497 unsafe), averaging 9.01 turns and 3.95k tokens, with 1,954 invoked tools drawn from pools spanning 2,084 available tools.
  arXiv  Detail & Related papers  (2026-04-02T13:26:20Z)
• AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions [64.85086226439954]
  We present SAFE, a benchmark for assessing the safety of embodied VLM agents on hazardous instructions.<n> SAFE comprises three components: SAFE-THOR, SAFE-VERSE, and SAFE-DIAGNOSE.<n>We uncover systematic failures in translating hazard recognition into safe planning and execution.
  arXiv  Detail & Related papers  (2025-06-17T16:37:35Z)

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.