safety monitor

Data Community

Skill notes

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:

Fluxly profile Runtime and permissions are inferred by Fluxly static checks, not author declarations or runtime test results.
Domain
Data
Author-declared agents
No explicit declaration found; this is not inferred or tested compatibility
Static check
94 / 100 · heuristic scan, not runtime safety proof
Runtime evidence
Not run; no isolated runtime test evidence is currently recorded
Author / version / license
@majiayu000 · MIT
Token usage
Lean
Setup complexity
Guided setup
External API key
Not required
Operating systems
Unspecified (assume cross-platform)
Runtime requirements
No explicit requirements detected
Detected file/system behavior
  • Read-only
  • Shell exec
Network behavior
Local-only
Install commands
None (reference only)

Heads up: Tool permissions are not declared; actual access depends on the runtime.

Author source file SKILL.md

# 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

1.  **Content Inspection**: Scans text for dangerous content.
2.  **LLM-based Audit**: Uses a separate LLM call to verify safety.
3.  **Status Reporting**: Returns 'approved', 'flagged', or 'rejected'.

## Workflow

1.  **Input**: Text content to check.
2.  **Execute**: Run the safety agent.
3.  **Output**: JSON status report.

## Example Usage

**User**: "Check this drug proposal for safety."

**Agent Action**:
```bash
python3 Skills/Clinical/Safety/safety_agent.py
```

Discussion

Powered by GitHub Discussions. Sign in with GitHub to comment, react, or subscribe.