projects-quick
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): No malicious behavior, obfuscation, or persistence mechanisms were detected. The skill performs standard information retrieval tasks using 'Read' and 'Glob' tools to summarize local markdown files.
- [PROMPT_INJECTION] (SAFE): While the skill processes data from external files (README.md, WORKLOG) which could contain indirect prompt injections, the risk is mitigated by the lack of high-privilege tools like Shell or Network. Ingestion points: ideas/CLAUDE.md, ideas/ideas/[project]/README.md, project-brief.md, WORKLOG. Boundary markers: None. Capability inventory: Read, Glob. Sanitization: None.
Audit Metadata