{
  "id": 18262,
  "url": "https://arxiv.org/abs/2608.09732v1",
  "title": "ColluSkill: Adversarial Cross-Skill Composition for Evading Agent Skill Scanners",
  "summary": "Agent skills are emerging as an important attack surface in LLM-based agent systems. Through an empirical study of existing skill scanners, we find that current defenses mainly inspect individual skills, leaving risks from cross-skill composition insufficiently examined. This creates a practical blind spot: multiple locally plausible skills may pass security checks while collectively forming a harmful workflow during agent execution. To investigate this threat, we propose ColluSkill, a collusive",
  "authors": "Puyu Zeng, Simeng Qin, Jingzhi Li, Ju Jia, Zheli Liu, Xiaojun Jia",
  "category": "research",
  "topics": "agents-autonomy,finance-investment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-10T15:32:44.000Z",
  "fetched_at": "2026-08-11T05:10:37.351Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/18262",
  "original_url": "https://arxiv.org/abs/2608.09732v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}