fda-database
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from the external openFDA API (api.fda.gov), which creates a surface for indirect prompt injection where instructions embedded in the API response could influence the agent's behavior.
- Ingestion points: Data enters the agent's context through the
_make_requestmethod inscripts/fda_query.py, which parses JSON responses from the openFDA API. - Boundary markers: The skill does not implement delimiters or explicit instructions to ignore potentially malicious content within the external API responses.
- Capability inventory: The skill possesses network GET capabilities (to api.fda.gov) and local file writing capabilities for the response cache in the
fda_cachedirectory. - Sanitization: The skill relies on standard JSON parsing without additional content sanitization or validation of the retrieved data.
Audit Metadata