Metraipolis › archive › dc_fcd916e9ee73
CompoSkill: Compositional Skill Chain Attacks from Individually Scanner-Passing LLM Agent Skills — arXiv:2608.16246
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.16246
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T18:07:06.279Z
- SHA-256 of the archived text
23db60ab69553514ce145f8ce40c061bc8bec9ec069287ea0affc2cf0488950d- Stable URL of this page
https://metraipolis.com/documento/dc_fcd916e9ee73
How to cite
CompoSkill: Compositional Skill Chain Attacks from Individually Scanner-Passing LLM Agent Skills — arXiv:2608.16246 — arXiv (en), https://arxiv.org/abs/2608.16246 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fcd916e9ee73 (Metraipolis archive dc_fcd916e9ee73, sha256 23db60ab69553514ce145f8ce40c061bc8bec9ec069287ea0affc2cf0488950d)
BibTeX
@misc{dcfcd916e9ee73,
title = {CompoSkill: Compositional Skill Chain Attacks from Individually Scanner-Passing LLM Agent Skills — arXiv:2608.16246},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.16246},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fcd916e9ee73; sha256 23db60ab69553514ce145f8ce40c061bc8bec9ec069287ea0affc2cf0488950d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16246. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Autonomous AI agents tackling Long Horizon Tasks depend on marketplace skills that are certified one at a time: a scanner returns a safety verdict for each skill and declares the ecosystem safe if every package passes. We show that this assumption fails under skill composition. A skill may pass the per-skill scanner individually yet participate in a risky composition when an agent connects its outputs, capabilities, or side effects with those of other scanner-passing skills. This makes skill composition risk a path level property rather than a node level property, explaining why existing skill scanners that inspect individual packages achieve limited interception. To study this threat, we present CompoSkill, a framework that constructs skill composition attacks through a dual attacker system. The white-box attacker knows the victim's installed skill pool and directly injects explicit skill-id sequences; the black-box attacker knows only a role profile, downloads the top marketplace skills for that scenario, builds a Skill Composition Graph, and searches for high risk chains whose implicit lures never name skill identifiers. We further construct CompoSkill-Bench, a benchmark of 1,140 records built from long-horizon professional workflows across five threats and six scenarios on OpenClaw and Nanobot. CompoSkill achieves risk Chain Formation Rates (CFR) up to 83.3% in the white box setting and 80.6% in the black box setting, while existing skill scanners block only a limited fraction of the risky compositions. Finally, we observe a bridge-bonus-then-hop-decay pattern: a bridge skill can increase attack success, but Attack Success Rate (ASR) decreases once additional hops make the risk chain longer than three skills. These results expose a systematic gap in single skill certification for autonomous AI agents. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI). Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.16246 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T16:29:14.098Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).