ai-health
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing external health data.
- Ingestion points: The skill reads several external data sources including
profile.json, lifestyle data, mental health data, and medical history data as described inSKILL.md. - Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the processing logic.
- Capability inventory: The skill utilizes the
Writetool to save generated HTML reports to thedata/ai-reports/directory. - Sanitization: There is no evidence of sanitization or validation of the ingested health data before it is used in analysis or report generation.
Audit Metadata