vue-expert
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): No instructions were found that attempt to bypass safety filters or override agent behavior.
- [Data Exposure & Exfiltration] (SAFE): The skill accesses local project metadata and saves output to a specific directory; no credential harvesting or exfiltration patterns detected.
- [Remote Code Execution] (SAFE): No remote script downloads or dangerous execution patterns identified.
- [Indirect Prompt Injection] (LOW): The skill ingests untrusted project documentation. Ingestion points: project_overview.md, architecture_patterns.md, type_patterns.md, testing_patterns.md. Boundary markers: relies on standard shared loading patterns. Capability inventory: write access to /claudedocs/. Sanitization: not specified.
Audit Metadata