nhcx-payer-communication

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

• Third-party content exposure detected (medium risk: 0.30). The workflow consumes outsider-authored free text via inbound webhook callbacks (C9. Communication), which process incoming hospital-submitted FHIR communication payloads containing unconstrained text strings and attachments.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The instruction mandates checking https://raw.githubusercontent.com/nha-in/nhcx-package/main/skills/manifest.json and https://api.github.com/repos/nha-in/nhcx-package/releases/latest to download and execute skill updates at runtime, which constitutes an unverifiable runtime external dependency from a weak or unofficial provenance path.