travel-health-analyzer
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-supplied travel history and medical records, and reads from external JSON files (e.g.,
data/travel-health-tracker.json), creating a surface for indirect prompt injection. - Ingestion points: User input for travel plans/medical history and local data files stored in the
data/directory. - Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the skill definitions.
- Capability inventory: The skill utilizes file system tools (
Read,Write,Grep,Glob) to manage health trackers and logs. - Sanitization: No explicit validation, escaping, or sanitization of the health data or destination risk information is described.
- [DATA_EXPOSURE]: The skill is intended to manage and store highly sensitive Protected Health Information (PHI) and Personal Identifiable Information (PII).
- The skill handles data including full names, dates of birth, blood types, chronic medical conditions, allergy history, and medications.
- The documentation mentions the storage of passport numbers, which is not strictly necessary for health risk assessment and increases the sensitivity of the stored data.
- The generation of emergency cards with QR codes linking to cloud storage (even if simulated) indicates a mechanism for exposing medical data to external entities.
Audit Metadata