nhcx-payer-preauth
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill includes functionality to automatically check for, download, and install updates from the vendor's official GitHub repository at
https://github.com/nha-in/nhcx-package. It also retrieves its core 'Knowledge Source' (FHIR examples, mappings, and protocol rules) from this repository. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process complex medical data (FHIR bundles) from untrusted external sources (hospitals).
- Ingestion points: Inbound HTTP POST requests received via the
Receive(G8) andCallback Door(C1) components are parsed into the agent's context. - Boundary markers: The provided instructions do not specify the use of boundary markers or instructions to ignore embedded commands when the agent evaluates external data.
- Capability inventory: The agent is instructed to perform network operations (
gateway.send), manage local file archives, and perform extensive database writes across various clinical and financial models. - Sanitization: While the skill uses structured FHIR parsers that provide schema-level validation, there is no explicit instruction to sanitize natural language fields for potentially malicious instructions.
Audit Metadata