family-health-analyzer
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external files which could potentially contain malicious instructions intended to influence the agent's behavior.
- Ingestion points: The skill reads from
data/family-health-tracker.json,data/hypertension-tracker.json,data/diabetes-tracker.json, anddata/profile.json(SKILL.md). - Boundary markers: There are no defined delimiters or instructions provided to the agent to disregard natural language commands that might be embedded within the health data fields.
- Capability inventory: The agent is granted
Read,Write,Grep, andGlobtools, which provide a significant capability surface if an injection occurs. - Sanitization: The skill description lacks specific procedures for validating, filtering, or escaping the content of the ingested JSON files before processing them for risk assessment or report generation.
Audit Metadata