healthcare-mcp-hardened

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The SKILL.md workflow explicitly instructs the agent to configure and query external FHIR servers (for example the command using https://hapi.fhir.org/baseR4) and to fetch and interpret clinical resources, so the agent ingests untrusted third‑party data that can influence subsequent decisions or actions.