postman

Pass

Audited by Gen Agent Trust Hub on Nov 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest and process potentially untrusted external data, including project source code, OpenAPI specifications, and local configuration files (.postman.json), to generate or synchronize API collections.
  • Ingestion points: API source code analysis, OpenAPI specification files (passed to createSpec), and the .postman.json configuration file.
  • Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions when reading source code or specifications.
  • Capability inventory: The skill utilizes powerful capabilities including creating and updating collections (createCollection, putCollection), generating assets from specs (generateCollection), and executing automated API test suites (runCollection).
  • Sanitization: The skill mandates strict validation of all generated content against the official Postman Collection Format schema (v2.1.0) before submission to the API.
  • [EXTERNAL_DOWNLOADS]: The skill references and fetches the official Postman Collection schema from https://schema.getpostman.com/json/collection/v2.1.0/collection.json to perform mandatory validation. This is a legitimate resource provided by the vendor.
  • [DATA_EXPOSURE]: The skill provides guidance on handling sensitive data like API keys and tokens, explicitly instructing the use of environment variables and the type: "secret" attribute to ensure they are masked within the Postman interface.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 5, 2026, 08:17 AM