family-health-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill accesses files containing sensitive health information (PHI) and personally identifiable information (PII).
- Target files include
data/family-health-tracker.json,data/hypertension-tracker.json,data/diabetes-tracker.json, anddata/profile.json. - Access is limited to the local filesystem; no network exfiltration tools are enabled in the skill configuration.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external JSON files that could be manipulated to influence agent behavior if the source data is compromised.
- Ingestion points: Multiple JSON files in the
data/directory used for tracking health metrics and user profiles. - Boundary markers: Instructions do not specify delimiters or security instructions to prevent the agent from obeying commands embedded within the medical records.
- Capability inventory: The skill uses the
ReadandWritetools to process data and generate HTML reports. - Sanitization: Validation steps are present but focused on data integrity (e.g., relationship logic) rather than prompt safety or command filtering.
- [EXTERNAL_DOWNLOADS]: References authoritative health information from the official CDC website regarding family health history.
Audit Metadata