regulatory-affairs-head

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill and its associated scripts are focused on regulatory documentation and tracking. All scripts perform local operations using standard libraries with no network connectivity or privilege escalation attempts.
  • [INDIRECT_PROMPT_INJECTION]: A limited ingestion surface exists where the skill processes user-supplied medical device details through its utility scripts.
  • Ingestion points: Device specifications, intended use descriptions, and project metadata provided as input to scripts/regulatory_pathway_analyzer.py and scripts/regulatory_tracker.py.
  • Boundary markers: Scripts process input as discrete string variables via standard command-line arguments and user prompts.
  • Capability inventory: Capabilities are restricted to local terminal output and writing to a specific local JSON file (regulatory_submissions.json). There are no network requests, dynamic code execution (eval/exec), or sensitive file system access.
  • Sanitization: The skill utilizes standard JSON serialization for data storage, ensuring data integrity for the local tracking functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 02:33 PM
Security Audit — agent-trust-hub — regulatory-affairs-head