clinical-trials-search
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes clinical trial data from the external ClinicalTrials.gov API, creating a surface for potential indirect prompt injection. \n- Ingestion points: ClinicalTrials.gov API /studies and /studies/{nctId} endpoints described in the Technical Details section. \n- Boundary markers: The documentation does not specify the use of delimiters or instructions for the agent to ignore embedded commands in the trial data. \n- Capability inventory: The skill performs read-only data retrieval from a public government registry. \n- Sanitization: No sanitization or validation processes are mentioned for the retrieved content.
Audit Metadata