monarch-database
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves structured biomedical data from an external REST API and prints or saves it to the local file system, creating an attack surface for indirect prompt injection.
- Ingestion points: Data is fetched via 'requests.get' from api.monarchinitiative.org endpoints in SKILL.md.
- Boundary markers: No delimiters or instructions are used to distinguish external data from agent instructions.
- Capability inventory: The skill writes to the local file system using 'pandas' (CSV) and 'matplotlib' (PNG).
- Sanitization: No sanitization of the API-sourced text is performed prior to processing or output.
- [EXTERNAL_DOWNLOADS]: The skill instructions include the installation of standard Python packages from a public package registry.
- Evidence: 'pip install requests pandas matplotlib'.
Audit Metadata