postman-explore

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed to interact with Postman's official MCP server to explore collection structures. It uses standard tool-calling patterns and includes secure setup instructions using placeholders for credentials.
  • [PROMPT_INJECTION]: The skill processes external data from Postman collections, which constitutes a standard attack surface for indirect prompt injection. This is a common characteristic of data-exploration tools and is evaluated as safe due to the skill's limited read-only scope.
  • Ingestion points: Data enters the agent context via tools like getCollections, getCollection, and getCollectionRequest in SKILL.md.
  • Boundary markers: The prompt does not utilize explicit delimiters to separate external data from instructions.
  • Capability inventory: The skill's capabilities are restricted to fetching and displaying Postman metadata; it cannot execute shell commands, write to the filesystem, or perform arbitrary network requests.
  • Sanitization: Data retrieved from the Postman API is presented without additional sanitization or filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 10:21 AM