{"skill":{"slug":"ant-skill-review","displayName":"Skill Review","summary":"Security scanner for Claude Code Skill packages. Use when the user wants to audit, review, or check the safety of a Skill before installing — e.g. \"is this s...","tags":{"latest":"1.0.1"},"stats":{"comments":0,"downloads":87,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1775791767813,"updatedAt":1775791852682},"latestVersion":{"version":"1.0.1","createdAt":1775791767813,"changelog":"- Initial release of skill-review: a multi-agent security scanner CLI for Claude Code Skill packages.\n- Runs a two-phase scan: deterministic static pre-scan and LLM-driven 7-layer deep analysis.\n- Detects risks including prompt injections, credential theft, dynamic code loading, obfuscated scripts, vulnerable dependencies, system modifications, and insecure code patterns.\n- Outputs deterministic risk scoring and actionable install recommendations.\n- Supports JSON and multilingual reports, configurable via environment or JSON file.","license":"MIT-0"},"metadata":null,"owner":{"handle":"antaisecuritylab","userId":"s1769dnfmd232dyj6bvbe4xahs845f7v","displayName":"Ant AI Security Lab","image":"https://avatars.githubusercontent.com/u/271417607?v=4"},"moderation":{"isSuspicious":true,"isMalwareBlocked":false,"verdict":"suspicious","reasonCodes":["suspicious.dangerous_exec","suspicious.dynamic_code_execution","suspicious.llm_suspicious","suspicious.potential_exfiltration"],"summary":"Detected: suspicious.dangerous_exec, suspicious.dynamic_code_execution, suspicious.llm_suspicious (+1 more)","engineVersion":"v2.2.0","updatedAt":1775791852682}}