oral-health-analyzer
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from various external sources, including user health records, nutrition logs, and medication histories. This ingestion process represents a potential attack surface for indirect prompt injection where malicious instructions could be embedded within health data to influence agent behavior.
- Ingestion points: Data enters the agent context via user-provided health records and cross-module logs (nutrition, chronic disease, medication) as described in
SKILL.mdandreferences/detailed-guide.md. - Boundary markers: The skill incorporates medical disclaimers and emergency safety warnings in the
detailed-guide.mdbut lacks specific instruction delimiters for the health data itself. - Capability inventory: The skill is primarily focused on data analysis and providing educational suggestions; no high-risk capabilities like arbitrary file writes or network exfiltration were identified.
- Sanitization: There is no evidence of explicit sanitization or filtering of the processed health data before it is incorporated into the analysis prompts.
Audit Metadata