clinicaltrials-database
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill connects to the official ClinicalTrials.gov API (https://clinicaltrials.gov/api/v2), which is a well-known and trusted service maintained by the U.S. National Library of Medicine.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests clinical trial data from an external API, creating a surface for potential indirect prompt injection.
- Ingestion points: Study data and summaries are fetched from the ClinicalTrials.gov API using the search_studies and get_study_details functions in scripts/query_clinicaltrials.py.
- Boundary markers: No specific delimiters or safety instructions are used when passing the API data to the agent.
- Capability inventory: The skill is limited to performing network GET requests to a trusted government domain and reading the resulting JSON or CSV data.
- Sanitization: No specific sanitization or filtering of the API content is implemented in the scripts.
Audit Metadata