imaging-referral

Pass

Audited by Gen Agent Trust Hub on Oct 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security threats detected. The skill provides static templates and clinical guidelines for medical imaging referrals. It does not interact with the host system or external network.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied clinical information to generate referrals, representing a data ingestion surface. Evidence analysis:\n
  • Ingestion points: User-provided clinical symptoms, history, and demographics in the referral generation prompt.\n
  • Boundary markers: None present.\n
  • Capability inventory: No subprocess calls, dynamic code execution (eval/exec), file system access, or network operations are present in the skill instructions or examples.\n
  • Sanitization: Not implemented, but the lack of exploitable capabilities mitigates this risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 5, 2026, 05:08 PM