Metraipolis › archive › dc_3d690e39dcb2
SKILLLITE: Evidence-Guided Malicious Skill Auditing with Compact LLMs — arXiv:2609.36879
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.36879
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T16:26:28.168Z
- SHA-256 of the archived text
0bed935d37e1adbbef0566f0c2a69a71c6f14ed02c273ee22b4a9a8b4e94cb06- Stable URL of this page
https://metraipolis.com/documento/dc_3d690e39dcb2
How to cite
SKILLLITE: Evidence-Guided Malicious Skill Auditing with Compact LLMs — arXiv:2609.36879 — arXiv (en), https://arxiv.org/abs/2609.36879 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3d690e39dcb2 (Metraipolis archive dc_3d690e39dcb2, sha256 0bed935d37e1adbbef0566f0c2a69a71c6f14ed02c273ee22b4a9a8b4e94cb06)
BibTeX
@misc{dc3d690e39dcb2,
title = {SKILLLITE: Evidence-Guided Malicious Skill Auditing with Compact LLMs — arXiv:2609.36879},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.36879},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3d690e39dcb2; sha256 0bed935d37e1adbbef0566f0c2a69a71c6f14ed02c273ee22b4a9a8b4e94cb06},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36879. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
As LLM-based agents perform increasingly complex tasks, Agent Skills have emerged as a flexible mechanism for extending their capabilities. An Agent Skill packages task-specific instructions with executable components and auxiliary resources to provide specialized functionalities. However, the growing adoption of third-party Skills introduces a new supply-chain attack surface. Malicious Skills can embed harmful behaviors that abuse agent privileges and compromise the agent execution environment or accessible resources. Although recent LLM-based malicious Skill auditing approaches have achieved promising performance, they often rely on capable commercial LLMs. How to achieve effective auditing with compact, locally deployable LLMs in security-sensitive and resource-constrained settings remains largely unexplored. Our investigation reveals that compact LLMs struggle to identify malicious behaviors hidden in complex Skill packages. This difficulty arises from both the implicit nature of such behaviors and the limited reasoning capacity of compact LLMs. To address these challenges, we propose SKILLLITE, an evidence-guided agentic framework for malicious Skill detection. SKILLLITE effectively extracts security-relevant behaviors and infers the intended functionality from complex Skill packages. It then employs a compact LLM to assess the maliciousness of the Skill based on the observed behaviors and their functional context. Experiments show that SKILLLITE improves malicious Skill detection across different compact LLM backbones and outperforms existing representative auditing baselines. Its effectiveness generalizes to behaviorally confirmed in-the-wild malicious Skills. Meanwhile, SKILLLITE maintains a low inference latency, supporting its practical deployment. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI). Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.36879 — 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 2026-10-07T15:54:53.900Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).