paperAugust 2026Unreviewed

EvoSkill Injection: Red-Teaming Autonomous Skill Generation and Evolution in Self-Evolving Agents

Doyun Kim, Chanwoo Kim, Sugyeong Eo, Yeo-Chan Yoon, Chanjun Park

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 EvoSk

Framework mappings

NIST AI Risk Management Framework

MEASUREMeasure

Suggested from the entry's categories.

Cite

@misc{kim2026evoskill,
  title = {{EvoSkill Injection: Red-Teaming Autonomous Skill Generation and Evolution in Self-Evolving Agents}},
  author = {Doyun Kim and Chanwoo Kim and Sugyeong Eo and Yeo-Chan Yoon and Chanjun Park},
  year = {2026},
  month = aug,
  eprint = {2608.30429},
  archivePrefix = {arXiv},
  url = {https://www.semanticscholar.org/paper/74b1d8292cfadce66a9d3467f4fcdd8246f7ba73}
}