Research · curated 20 Aug 2026
SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills
First reported arxiv.org
Coverage timeline
Single-source research — first reported, latest, and curated coincide.
Why it matters
SkillSieve addresses an emerging supply-chain threat class where installed AI agent skills can smuggle prompt injection alongside credential theft and data exfiltration, giving defenders a measurable, deployable pipeline to triage malicious packages before they run with agent privileges.
SkillSieve is a hierarchical triage framework for detecting malicious AI agent skills—packages that combine natural-language SKILL.md instructions with executable code and inherit an agent's filesystem, credential, and network access. The framework layers recall-oriented regex/AST/metadata triage, four parallel LLM security sub-tasks, and a three-model debating jury, reaching F1=0.929 across 49,592 real ClawHub skills, a 390-skill benchmark, and 100 adversarial samples; code, labels, and results are open-sourced. Related audits (Snyk's ToxicSkills) reportedly found 13.4% of scanned skills contained critical issues including malware, prompt injection, and credential exfiltration.