fhir-data-access

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill is installed from the Open-Medica GitHub repository, which is a vendor-owned resource associated with the skill author.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8) as it processes clinical data from external FHIR servers.
  • Ingestion points: Data enters the context via FHIR API responses from medical endpoints specified in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the retrieval instructions.
  • Capability inventory: The skill is capable of network operations (REST API calls) and clinical data aggregation.
  • Sanitization: No sanitization or validation logic is defined to protect against malicious instructions embedded in clinical resource fields like notes or descriptions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 01:03 PM
Security Audit — agent-trust-hub — fhir-data-access