postman

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly calls searchPostmanElements (noted in the "Generate Client Code" and "Discover APIs" workflows and in references/mcp-limitations.md) to fetch collections from the public Postman network and then reads endpoint descriptions/specs from those public, user-generated sources to drive discovery and code-generation decisions, which could allow indirect prompt injection.