clinical-trial-protocol-skill
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references and fetches regulatory data from official government domains, including clinicaltrials.gov and multiple fda.gov databases (510(k), PMA, De Novo, Drugs@FDA). These are well-known and trusted sources for medical regulatory information.
- [COMMAND_EXECUTION]: The orchestrator invokes a local Python script
scripts/sample_size_calculator.pyusing a subprocess call to perform statistical calculations. This is a standard utility function, and the script does not utilize dangerous dynamic execution patterns. - [INDIRECT_PROMPT_INJECTION]: The workflow allows for the ingestion of 'initial context' (user documentation) and research findings into protocol templates. While this creates an ingestion point for external data, the skill's capabilities are focused on document generation and do not provide a path for high-privilege command execution or unauthorized data exfiltration.
Audit Metadata