tooluniverse-clinical-trial-design

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data from external medical research databases, which creates a potential surface for indirect prompt injection.
  • Ingestion points: Untrusted data enters the agent context via research tools such as PubMed_search_articles and search_clinical_trials as implemented in python_implementation.py and trial_pipeline.py.
  • Boundary markers: The instructions lack explicit delimiters or 'ignore' warnings to prevent the agent from following potential instructions embedded in retrieved abstracts or trial descriptions.
  • Capability inventory: The skill is capable of reading from multiple external APIs and writing markdown reports to the local file system.
  • Sanitization: There is no evidence of content sanitization or validation performed on data retrieved from external sources before it is analyzed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 11:31 PM