SkillPoison demonstrates that self‑improving large language model agents can be progressively poisoned through successful experiences without any single trajectory being malicious. The framework constructs successful experiences that reinforce a target behavior, then removes contextual constraints so the skill extractor generalizes to harmful behavior when misapplied. Experiments on three benchmarks show a 95.71% attack success rate while all injected experiences remain task‑correct and pass verification and lexical inspection.
arXiv:2602. 14211v3 Announce Type: replace-cross Abstract: Agent skills extend LLM agents with task-specific instructions, executable scripts, and auxiliary resources, improving reusability but creating a new supply-chain attack surface.
arXiv:2609.36879v1 Announce Type: cross Abstract: As LLM-based agents perform increasingly complex tasks, Agent Skills have emerged as a flexible mechanism for extending their capabilities. An Agent...
The paper introduces PERSIST, a method that allows attackers to inject malicious actions into large language model agents by linking attacker-chosen actions to useful functions while minimizing source inspection and suspicion. PERSIST builds helper functions from simulated executions and embeds them in separate modules, enabling the agent to perform both user tasks and attacker objectives. Experiments on SkillsBench and Skill-Inject demonstrate that frozen skill packages transfer across multiple agent–model configurations, generalize to unseen tasks, and increase harmful-effect rates compared to baselines.
The paper introduces a new skill poisoning technique for large language model agents that decouples the pretext (rationale) from the actuation (operation). By separating these two risk‑realization factors, the authors create coordinated pretext‑actuation skill pairs that allow malicious actions to remain hidden within legitimate agent behavior. An automated framework is presented to discover execution dependencies, synthesize these skill pairs, and refine them through closed‑loop feedback, achieving high attack success in both single‑session and persistent scenarios.
arXiv:2608. 09732v1 Announce Type: cross Abstract: Agent skills are emerging as an important attack surface in LLM-based agent systems.
arXiv:2608. 05563v1 Announce Type: cross Abstract: Self-evolving skill (SES) systems distill agent trajectories into persistent skills, allowing untrusted experience to become trusted instruction.
arXiv:2608.30429v1 Announce Type: new Abstract: LLM-based agent systems increasingly adopt skill-based architectures to reduce repetitive reasoning costs and improve stable, efficient task execution....
arXiv:2608. 08303v1 Announce Type: new Abstract: Agentic skills improve large language model (LLM) agents by encoding reusable procedures for complex tasks.
arXiv:2602. 06547v4 Announce Type: replace-cross Abstract: LLM-based coding agents increasingly rely on third-party extensions called skills, which bundle natural language instructions and helper scripts that execute with full user privileges.
arXiv:2610.17727v2 Announce Type: cross Abstract: Agent skills turn natural-language instructions into actions, creating a security challenge: legitimate automation and malicious behaviour can look d...
arXiv:2602. 06547v3 Announce Type: replace-cross Abstract: LLM-based coding agents increasingly rely on third-party extensions called skills, which bundle natural language instructions and helper scripts that execute with full user privileges.
arXiv:2609.39065v1 Announce Type: cross Abstract: LLM agents increasingly rely on installable skills, which are packages of instructions, code, and resources that equip them with task-specific capabi...