By name: 'safety-monitor' description: 'Safety Monitor' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command
Safety Monitor Agent
Agent responsible for compliance and safety checks. It inspects content for safety violations, toxins, or medical misinformation.
When to Use This Skill
- Before returning any medical advice to a user.
- To audit generated molecules for toxicity.
- To check for Protected Health Information (PHI) leaks.
Core Capabilities
- Content Inspection: Scans text for dangerous content.
- LLM-based Audit: Uses a separate LLM call to verify safety.
- Status Reporting: Returns 'approved', 'flagged', or 'rejected'.
Workflow
- Input: Text content to check.
- Execute: Run the safety agent.
- Output: JSON status report.
Example Usage
User: "Check this drug proposal for safety."
Agent Action:
python3 Skills/Clinical/Safety/safety_agent.py