Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation

Abstract

Reusable skills are becoming a fundamental building block of Large Language Model (LLM) agents, enabling capabilities to be packaged, shared, and reused across diverse applications. However, existing security research primarily focuses on prompt injection and runtime execution, leaving security risks throughout the broader skill lifecycle largely unexplored. In this paper, we present SkillSec-Eval, a lifecycle-aware framework for systematically evaluating the security of reusable agent skills. W

Categories

Framework mappings

Suggested from the entry's categories.

@misc{badhe2026agent,
  title = {{Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation}},
  author = {Sanket Badhe and Priyanka Tiwari},
  year = {2026},
  month = jul,
  eprint = {2607.13987},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.13987}
}