postman-collection-generator
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data by scanning and parsing application source code to extract API route metadata. While this is the primary functionality of the tool, it represents a potential surface for indirect prompt injection if the scanned codebase contains malicious instructions embedded in comments or route names intended for the agent processing the output.
- Ingestion points: Application source code files read by scanning functions in
scripts/generate-postman.ts,scripts/scan-nextjs-routes.ts, andscripts/scan-fastify-routes.ts. - Boundary markers: None identified in the provided static analysis logic.
- Capability inventory: Local file system read and write access (
fs). - Sanitization: Extracted metadata is structured into a JSON collection, but individual string values are not explicitly sanitized for potential LLM instructions.
- [EXTERNAL_DOWNLOADS]: The skill references the official Postman collection schema URL (
https://schema.getpostman.com/json/collection/v2.1.0/collection.json). This reference targets a well-known service domain for standard configuration purposes and does not contribute to verdict escalation.
Audit Metadata