Hiding in Plain Sight: Decoupling Pretext from Actuation for Skill Poisoning in LLM Agents

arXiv:2609.39352 · cs.CR, cs.AI · Submitted 2026-09-30 · Read on arXiv

cs.CR, cs.AI

Submitted: 2026-09-30

Updated: 2026-09-30

Code: https://github.com/Wenxin-buaa/CoordPoison

Terminology

• Steering — 65× in this paper · explained in 2 episodes
• Grounding — 33× in this paper · explained in 3 episodes
• Trace — 32× in this paper · explained in 2 episodes
• Decoupling — 16× in this paper · explained in 2 episodes
• Benchmark — 11× in this paper · explained in 2 episodes
• Transferability — 7× in this paper · explained in 4 episodes
• Agent Skills — 6× in this paper · explained in 1 episode
• Verification — 6× in this paper · explained in 2 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Alignment — 4× in this paper · explained in 1 episode
• Attack Success Rate — 4× in this paper
• Provenance — 4× in this paper · explained in 3 episodes
• Adaptation — 3× in this paper · explained in 1 episode
• Consistency — 3× in this paper · explained in 3 episodes
• Core — 3× in this paper · explained in 2 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Abstraction — 2× in this paper · explained in 1 episode
• Agent Architectures — 2× in this paper · explained in 1 episode
• Failure Modes — 2× in this paper · explained in 3 episodes
• Failure Taxonomy — 2× in this paper · explained in 2 episodes
• LLM judge — 2× in this paper · explained in 2 episodes
• Agent Harness — 1× in this paper · explained in 2 episodes
• Attack Success Rate (ASR) — 1× in this paper · explained in 2 episodes
• Domain Adaptation — 1× in this paper · explained in 5 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Multi-Agent System — 1× in this paper · explained in 6 episodes
• Reasoning Traces — 1× in this paper · explained in 3 episodes
• Self-Evolving Agents — 1× in this paper · explained in 2 episodes
• Topological Order — 1× in this paper · explained in 2 episodes

Sources

• SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems
• Poise: Position-Aware One-Instruction Skill Injection for Silent Execution on LLM Agents
• SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents
• SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces
• Convergent Detour Hijacking: Task-Preserving Resource Amplification in Skill-Based LLM Agents
• Exploiting LLM Agent Supply Chains via Payload-less Skills
• SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction
• Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems
• Under the Hood of SKILL.md: Semantic Supply-chain Attacks on AI Agent Skill Registry
• Agent Skills Enable a New Class of Realistic and Trivially Simple Prompt Injections
• Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
• BadSkill: Backdoor Attacks on Agent Skills via Model-in-Skill Poisoning
• When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems
• Benign in Isolation, Harmful in Composition: Security Risks in Agent Skill Ecosystems
• SkillJack: Persistent Skill Backdoors in Self-Evolving Agents
• ColluSkill: Adversarial Cross-Skill Composition for Evading Agent Skill Scanners
• AgentTrap: Measuring Runtime Trust Failures in Third-Party Agent Skills

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs