skills/nha-in/docs/nhcx-preauth/Gen Agent Trust Hub

nhcx-preauth

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads essential integration assets, including FHIR schema 'pins' and test fixtures, from the official vendor repository at github.com/nha-in/nhcx-package. It also provides instructions for downloading an optional FHIR adapter from github.com/nha-in/nhcx-adapter if required by the implementation environment.
  • [REMOTE_CODE_EXECUTION]: A setup script (scripts/fetch-package.sh) automates the retrieval and extraction of the vendor's data package. This script uses curl or wget to download assets and executes Python logic to verify SHA256 checksums before unzipping the content.
  • [INDIRECT_PROMPT_INJECTION]: Ingestion points: Received messages from the NHCX network (e.g., ClaimResponse) enter the agent context via modules 7.3, 7.8, and 7.10. Boundary markers: The skill design utilizes structured FHIR JSON and JWE encryption as boundaries for external data. Capability inventory: Modules trigger network requests to ABDM gateways and manage local file archives. Sanitization: The methodology mandates strict field mapping and the use of the HL7 FHIR validator to prevent untrusted data from influencing agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 07:25 AM