MalSkillBench supplies the first sandbox-verified dataset of malicious agent skills and shows that existing detectors achieve high recall on code injection but collapse on prompt injection and agent-control attacks.
Formal analysis and supply chain security for agentic AI skills
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
years
2026 9roles
baseline 1polarities
baseline 1representative citing papers
The paper defines Agent Skill Supply Chains (ASSCs) and SkillDepAnalyzer to extract and analyze dependency graphs from over 1.43 million LLM agent skills, revealing structural patterns and security signals.
SIGIL cryptographically seals the audit-runtime gap for LLM skills via an on-chain registry with four publication types, DAO vetting, and a runtime verification loader that enforces integrity and permissions.
Runtime Skill Audit introduces targeted runtime probing to detect malicious LLM agent skills, reporting 90% accuracy and resilience to self-evolving attacks on 100 skills versus static baselines.
About 18.2% of structurally flagged skill pairs represent genuine compositional safety risks in agent skill registries, with exploitation gated by host model behavior.
BIV audits AI agent skills at scale, finding 80% deviate from declared behavior on 49,943 skills and achieving 0.946 F1 for malicious skill detection.
SkillVetBench is a two-stage benchmark combining natural-language semantic vetting and instrumented sandbox execution to detect and provide runtime evidence for malicious skills in open agent platforms, with experiments showing static methods miss up to 89% of threats.
Qualixar OS provides a runtime for multi-agent AI systems with support for 12 topologies, LLM-driven team design, dynamic routing, consensus judging, content attribution, and protocol bridging, achieving 100% accuracy on a custom 20-task suite at $0.000039 mean cost per task.
citing papers explorer
-
Behavioral Integrity Verification for AI Agent Skills
BIV audits AI agent skills at scale, finding 80% deviate from declared behavior on 49,943 skills and achieving 0.946 F1 for malicious skill detection.