clinical-guideline-navigator
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data in the form of clinical scenarios provided by users. While this presents a surface for indirect prompt injection, the risk is negligible as the skill lacks high-impact capabilities like system command execution or network exfiltration.
- Ingestion points: User-provided clinical scenarios (e.g., diagnosis, patient vitals, medical history) mentioned in the clinical use cases and example usage sections of SKILL.md.
- Boundary markers: None present; the instructions do not specify delimiters for user input.
- Capability inventory: None detected; the skill performs text-based summarization and comparison of clinical guidelines.
- Sanitization: None present; no evidence of input validation or filtering.
- [SAFE]: The skill consists entirely of markdown documentation. The installation instruction uses a standard package manager command pointing to the author's official organization repository, which is consistent with the skill's stated source and authorship.
Audit Metadata