clinpgx-database
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves pharmacogenomic data from an external API, which creates a surface for potential indirect prompt injection attacks.
- Ingestion points: Data is ingested from api.clinpgx.org within the scripts/query_clinpgx.py file.
- Boundary markers: No explicit boundary markers or isolation instructions are used when passing API data to the agent context.
- Capability inventory: The skill is capable of performing network GET requests and writing to local JSON cache files.
- Sanitization: The skill performs standard JSON parsing but does not sanitize or filter the content of the API response strings.
Audit Metadata