occupational-health

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE]: The skill collects and stores sensitive personal information, specifically occupational health data such as symptoms (neck pain, wrist pain, etc.), their severity, and work-related habits. This data is written to a local file at data/occupational-health-records.json. While this is a legitimate use case for a health management skill, users should be aware of the storage of sensitive health information on the filesystem.
  • [INDIRECT_PROMPT_INJECTION]: The skill represents an ingestion surface for untrusted user input. It parses natural language descriptions of work and health to populate a structured JSON report.
  • Ingestion points: User input provided during the assessment flow (e.g., 'office work, 8 hours a day, neck pain').
  • Boundary markers: None explicitly defined in the prompt instructions.
  • Capability inventory: Uses the Write tool to create or update the records file.
  • Sanitization: The skill utilizes a strict JSON schema (schema.json) with defined enums for work types and health issues, which serves as a validation layer for the parsed data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 05:26 AM
Security Audit — agent-trust-hub — occupational-health