regulatory-affairs-head

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides legitimate informational content regarding FDA, EU MDR, and other global regulatory pathways. No evidence of prompt injection, data exfiltration, or malicious commands was found.
  • [SAFE]: The Python script scripts/regulatory_tracker.py is a standard utility that manages a local JSON file to track regulatory milestones. It does not use any third-party dependencies or perform network operations.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a potential ingestion surface for indirect prompt injection via its tracking script.
  • Ingestion points: scripts/regulatory_tracker.py reads content from regulatory_submissions.json to generate reports.
  • Boundary markers: None; the report is generated as plain text.
  • Capability inventory: The script has local file system read/write access for its data file and prints reports to the agent's console.
  • Sanitization: Data read from the JSON file is not sanitized before being printed in the status report.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 12:32 PM
Security Audit — agent-trust-hub — regulatory-affairs-head