A Finger on the Scale: Covert Policy Steering through Agentic Skills

• URL: http://arxiv.org/abs/2609.02564v1
• Date: Wed, 02 Sep 2026 13:15:14 GMT
• Title: A Finger on the Scale: Covert Policy Steering through Agentic Skills
• Abstract summary: Reusable agent skills extend large language model (LLM) agents with task procedures, tool-use guidance, and output constraints.<n>We formalize Skill Policy Integrity, which requires a Skill-induced policy to remain aligned with its declared functionality and the user-authorized objective.<n>We present SkillShift, a constrained black-box framework for covert policy steering without explicit target command injection or task hijacking.
• Score: 42.71897827897363
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reusable agent skills extend large language model (LLM) agents with task procedures, tool-use guidance, and output constraints. Yet these skills also act as externalized behavioral policies, which create a supply-chain risk: a third-party skill may preserve the declared task and valid output interface while covertly redirecting agent decisions toward an undisclosed objective. We formalize Skill Policy Integrity, which requires a Skill-induced policy to remain aligned with its declared functionality and the user-authorized objective. We further present SkillShift, a constrained black-box framework for covert policy steering without explicit target command injection or task hijacking. It combines semantically plausible policy edits with hierarchical validation, failure-guided optimization, and strategy compression to preserve effectiveness, output validity, transferability, and inconspicuousness. We instantiate this threat in agentic commerce and software dependency use, with SkillShift achieving attacker-favored selection rates of 81.33% and 63.33% while maintaining a 100% utility-preserving rate. The frozen policies also transfer without further optimization across heterogeneous LLM backends and agent environments. Moreover, the evaluated scanners fail to detect the constructed skills, motivating behavioral auditing of reusable skills as agent policy artifacts.

Related papers

• A Policy Algebra for Trust-Preserving Agentic AI Execution [5.943264605557423]
  We propose a policy algebra that defines the reliability envelope within which agent capability may be exercised.<n>The evaluation is interpreted as a reliability-capability trade-off rather than a capability benchmark.
  arXiv  Detail & Related papers  (2026-08-17T10:59:15Z)
• SkillGuard: A Permission Framework for Agent Skills [14.787581333168859]
  We present SkillGuard, a skill-centric permission framework that treats skills as permission-bearing executable artifacts.<n>We evaluate SkillGuard on 315 real-world skills and SkillInject.
  arXiv  Detail & Related papers  (2026-06-02T02:01:53Z)
• 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)
• Under the Hood of SKILL.md: Semantic Supply-chain Attacks on AI Agent Skill Registry [49.83108591873481]
  We study SKILL.md - only attacks across three registry-facing stages of the Agent Skill lifecycle.<n>We show that SKILL.md is not passive documentation but operational text that shapes which third-party capabilities agents find, trust, and use.
  arXiv  Detail & Related papers  (2026-05-12T02:11:54Z)
• Dynamic Skill Lifecycle Management for Agentic Reinforcement Learning [11.76119198695392]
  Large language model agents increasingly rely on external skills to solve complex tasks.<n>Existing methods assume external skills either accumulate as persistent guidance or internalized into the policy, leading to zero-skill inference.<n>We argue this assumption is overly restrictive, since with limited parametric capacity and uneven marginal contribution across skills, the optimal active skill set is non-monotonic, task- and stage-dependent.
  arXiv  Detail & Related papers  (2026-05-11T17:55:13Z)
• PolicyBank: Evolving Policy Understanding for LLM Agents [51.86716874651299]
  PolicyBank maintains structured, tool-level policy insights and iteratively refines them.<n>PolicyBank closes up to 82% of the gap toward a human oracle.
  arXiv  Detail & Related papers  (2026-04-16T20:29:30Z)
• SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement [66.44008181092832]
  LLM-based agent systems increasingly rely on agent skills sourced from open registries to extend their capabilities.<n>We introduce SkillAttack, a framework that verifies skill vulnerability exploitability through adversarial prompting.
  arXiv  Detail & Related papers  (2026-04-05T06:25:11Z)
• SoK: Agentic Skills -- Beyond Tool Use in LLM Agents [6.356997609995175]
  Agentic systems increasingly rely on reusable procedural capabilities, textita.k.a., agentic skills, to execute long-horizon reliably.<n>This paper maps the skill layer across the full lifecycle (discovery, practice, distillation, storage, composition, evaluation, and update)<n>We analyze the security and governance implications of skill-based agents, covering supply-chain risks, prompt injection via skill payloads, and trust-tiered execution.
  arXiv  Detail & Related papers  (2026-02-24T13:11:38Z)
• SkillJect: Automating Stealthy Skill-Based Prompt Injection for Coding Agents with Trace-Driven Closed-Loop Refinement [120.52289344734415]
  We propose an automated framework for stealthy prompt injection tailored to agent skills.<n>The framework forms a closed loop with three agents: an Attack Agent that synthesizes injection skills under explicit stealth constraints, a Code Agent that executes tasks using the injected skills and an Evaluate Agent that logs action traces.<n>Our method consistently achieves high attack success rates under realistic settings.
  arXiv  Detail & Related papers  (2026-02-15T16:09:48Z)
• Effective Red-Teaming of Policy-Adherent Agents [10.522087614181745]
  Task-oriented LLM-based agents are increasingly used in domains with strict policies, such as refund eligibility or cancellation rules.<n>We propose a novel threat model that focuses on adversarial users aiming to exploit policy-adherent agents for personal benefit.<n>We present CRAFT, a multi-agent red-teaming system that leverages policy-aware persuasive strategies to undermine a policy-adherent agent in a customer-service scenario.
  arXiv  Detail & Related papers  (2025-06-11T10:59:47Z)

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.