doctor-helper
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill package consists solely of Markdown files, providing instructions and templates for an AI agent. There are no scripts or binary files, which effectively mitigates common attack vectors like remote code execution.- [SAFE]: The skill defines a clear safety boundary by requiring a "gate check" for medical professionals and including persistent disclaimers stating that outputs are for reference only and not for clinical diagnosis.- [SAFE]: Mentions of external platforms like PubMed, Lexicomp, and UpToDate are used correctly as authoritative reference points for evidence-based medicine, not for dynamic data fetching or exfiltration.
Audit Metadata