clinicaltrials-database-search

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests clinical trial data, including text fields using CommonMark, from an external source. While the source is a known government entity, the processing of untrusted data poses a surface for indirect prompt injection.
  • Ingestion points: Trial data retrieved from clinicaltrials.gov/api/v2/studies in SKILL.md.
  • Boundary markers: Absent; data is interpolated into outputs without specific delimiters.
  • Capability inventory: File-system write access for CSV export in SKILL.md.
  • Sanitization: Absent; there is no explicit validation or escaping of the retrieved markdown content.
  • [EXTERNAL_DOWNLOADS]: The skill uses requests to fetch data from clinicaltrials.gov. This is a well-known service, and the operations are consistent with the skill's stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 03:35 PM
Security Audit — agent-trust-hub — clinicaltrials-database-search