nfeio-node-sdk
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data from webhooks and municipality API responses, which constitutes an indirect prompt injection attack surface.
- Ingestion points: Webhook request bodies (e.g., req.body in SKILL.md) and asynchronous responses from municipal tax servers managed by the SDK's polling utility.
- Boundary markers: The provided documentation describes technical API usage but does not specify explicit boundary markers or instructions to disregard instructions embedded within the processed data.
- Capability inventory: The SDK executes network operations via fetch to multiple vendor-owned API hosts (nfe.io, nfse.io) and includes functionality for writing fiscal documents to the local disk using node:fs.
- Sanitization: The skill documentation explicitly promotes security best practices, such as mandatory HMAC-SHA1 signature validation for webhooks and pre-flight validation of digital certificates using the CertificateValidator utility.
Audit Metadata