EvoSkill Injection: Red-Teaming Autonomous Skill Generation and Evolution in Self-Evolving Agents
- URL: http://arxiv.org/abs/2608.30429v1
- Date: Mon, 31 Aug 2026 08:25:03 GMT
- Title: EvoSkill Injection: Red-Teaming Autonomous Skill Generation and Evolution in Self-Evolving Agents
- Abstract summary: Self-evolving agents can generate, refine, and reuse skills from past experiences to enable continuous capability evolution.<n>However, autonomous skill evolution introduces a new attack surface in which malicious capabilities are generated, stored, and reused as legitimate skills.<n>In this paper, we define EvoSkill Injection as a threat model targeting the autonomous skill generation and evolution pipeline of self-evolving agents.
- Score: 18.945601649519478
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: LLM-based agent systems increasingly adopt skill-based architectures to reduce repetitive reasoning costs and improve stable, efficient task execution. Recent studies propose self-evolving agents that autonomously generate, refine, and reuse skills from past experiences to enable continuous capability evolution. However, autonomous skill evolution introduces a new attack surface in which malicious capabilities are generated, stored, and reused as legitimate skills. In this paper, we define EvoSkill Injection as a threat model targeting the autonomous skill generation and evolution pipeline of self-evolving agents. We further propose SARGE (Red-teaming Autonomous Skill Generation and Evolution in self-evolving agents), a red-teaming framework for evaluating this threat model through iterative generation, escalation, and reinforcement interactions. To support our framework, we construct EvoSkillBench, a benchmark dataset of malicious interaction trajectories for inducing malicious skill formation in self-evolving agents, and introduce EvoSkillSafetyBench, a post-attack benchmark for evaluating whether injected malicious skills are subsequently retrieved and activated as harmful behaviors. Our evaluation shows that SARGE induces malicious skill formation and that injected skills are persistently stored and repeatedly activated, highlighting the risk of persistent capability corruption.
Related papers
- Query-Only Backdoor Attacks on Self-Evolving Skills via Trajectory Poisoning [23.79611349616925]
Agentic skills improve large language model (LLM) agents by encoding reusable procedures for complex tasks.<n>Self-evolving skill systems have been developed to automatically construct and update skills from execution trajectories.<n>We propose Trajectory Backdoor Attack (TBA), a query-only attack that steers a trusted skill-evolution pipeline toward producing a backdoored skill.
arXiv Detail & Related papers (2026-08-08T19:31:19Z) - Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills [53.15216425100295]
We introduce Skill Self-Play (Skill-SP), a co-evolutionary framework comprising a proposer, a solver, and a skill controller.<n>The proposer generates challenging tasks conditioned on dynamically sampled skills; the solver explores candidate solutions to push its capability boundaries; and the skill controller collects execution feedback to update and expand the skill library.<n>This interactive co-evolution effectively bridges the gap between structured verification and open-ended exploration.
arXiv Detail & Related papers (2026-07-24T17:59:22Z) - SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction [89.03272793385054]
Agent skills occupy a privileged position in the agent workflow, rendering third-party skills a vulnerable attack surface.<n>We introduce SkillHarm, a benchmark of skill-based attacks across the skill-use lifecycle.<n>We show that current agents remain vulnerable with attack success rates up to 86.3% in FPP and 69.3% in SMP.
arXiv Detail & Related papers (2026-06-01T17:45:39Z) - MobEvolve: An Agentic Self-Evolving Heuristic System for Interpretable Human Mobility Generation [51.824145170051516]
MobEvolve is a self-evolving framework for human mobility generation.<n>It employs an agent to iteratively evolve its internal logic.<n>It significantly outperforms state-of-the-art deep generative and LLM-based methods.
arXiv Detail & Related papers (2026-06-01T03:46:25Z) - Learning Without Losing Identity: Capability Evolution for Embodied Agents [14.412476605788482]
We propose a capability-centric evolution paradigm for embodied agents.<n>We argue that a robot should maintain a persistent agent as its cognitive identity.<n>We present a unified framework in which capability evolution is decoupled from agent identity.
arXiv Detail & Related papers (2026-04-09T04:51:07Z) - EvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification [85.3692584167951]
Anthropic proposes the concept of skills for LLM agents to tackle multi-step professional tasks.<n>A tool is a single, self-contained function, whereas a skill is a structured bundle of interdependent multi-file artifacts.<n>EvoSkills is a self-evolving skills framework that enables agents to autonomously construct complex, multi-file skill packages.
arXiv Detail & Related papers (2026-04-02T06:43:20Z) - SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning [83.98129545309277]
We propose SkillRL, a framework that bridges the gap between raw experience and policy improvement.<n>Our approach introduces an experience-based distillation mechanism to build a hierarchical skill library SkillBank.<n> Experimental results on ALF, WebShop and seven search-augmented tasks demonstrate that SkillRL achieves state-of-the-art performance.
arXiv Detail & Related papers (2026-02-09T03:17:17Z) - Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents [58.69865074060139]
We study the case where an agent's self-evolution deviates in unintended ways, leading to undesirable or even harmful outcomes.<n>Our empirical findings reveal that misevolution is a widespread risk, affecting agents built even on top-tier LLMs.<n>We discuss potential mitigation strategies to inspire further research on building safer and more trustworthy self-evolving agents.
arXiv Detail & Related papers (2025-09-30T14:55:55Z)
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.