occupational-health-analyzer
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it reads and processes untrusted data from several external JSON files to generate health reports and recommendations.
- Ingestion points: The agent reads data from
data-example/occupational-health-tracker.json,data-example/sleep-tracker.json,data-example/fitness-tracker.json, anddata-example/mental-health-tracker.json. - Boundary markers: The skill contains explicit medical safety boundaries (e.g., "Does not perform occupational disease diagnosis") and disclaimers, but it lacks specific instructions for the agent to ignore potentially malicious instructions embedded within the health data itself.
- Capability inventory: The skill is granted
Read,Grep,Glob,Write, andEditpermissions, allowing it to both read from and modify the local filesystem based on its analysis. - Sanitization: There are no instructions to sanitize, escape, or validate the content of the ingested data beyond checking for file existence and basic structure.
Audit Metadata