regulatory-affairs-head

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security threats were detected. The skill is designed to provide regulatory guidance and management for medical device manufacturers.
  • [COMMAND_EXECUTION]: The skill includes a Python script (scripts/regulatory_tracker.py) intended to track submission statuses locally. The script utilizes standard library modules (json, datetime, dataclasses, enum) and performs only local file operations on regulatory_submissions.json. It does not execute arbitrary shell commands, access sensitive system paths, or perform network requests.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it processes external product information and stakeholder inputs to develop regulatory strategies.
  • Ingestion points: Product intended use, technology details, and target markets gathered in the 'New Product Regulatory Strategy' workflow (SKILL.md).
  • Boundary markers: None identified.
  • Capability inventory: Local file write capability through the scripts/regulatory_tracker.py tool.
  • Sanitization: No explicit sanitization or input validation logic is present in the skill instructions.
  • Analysis: The injection surface is limited to low-impact local tracking and strategy generation, with no high-privilege capabilities exposed to potential attackers via these inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 01:08 AM