clinicaltrials-database
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and process clinical trial data (such as brief summaries, titles, and eligibility criteria) from the external ClinicalTrials.gov API. This data constitutes untrusted content that could contain instructions meant to manipulate the agent's behavior.
- Ingestion points: The agent ingests trial data through API calls to
https://clinicaltrials.gov/api/v2/studiesas documented inSKILL.md. - Boundary markers: The instructions do not specify any boundary markers or delimiters to help the agent distinguish between the skill's instructions and the external data being processed.
- Capability inventory: The skill has the capability to perform network requests using the
requestslibrary and write output to the local file system (e.g., CSV export). - Sanitization: There is no mention of sanitizing or filtering the trial data retrieved from the API before it is added to the agent's context.
Audit Metadata