pubmed-database
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from an external API, creating a potential surface for indirect prompt injection.
- Ingestion points: The
esearchfunction inSKILL.mdretrieves and parses JSON data fromeutils.ncbi.nlm.nih.gov. - Boundary markers: No specific delimiters or safety instructions are used when interpolating external data into the agent's context.
- Capability inventory: The skill utilizes network capabilities via the
requestslibrary to fetch biomedical literature. - Sanitization: There is no evidence of sanitization or filtering of the retrieved content before it is processed.
- [EXTERNAL_DOWNLOADS]: The skill fetches configuration and literature data from the National Center for Biotechnology Information (NCBI) E-utilities API at
eutils.ncbi.nlm.nih.govusing the Pythonrequestslibrary.
Audit Metadata