postman

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

• Third-party content exposure detected (high risk: 0.70). The SKILL.md shows the skill uses the Membrane CLI to connect to Postman and run actions like "Get Collection" / "Get Workspace" (see "Popular actions" and "Running actions"), which fetch user-generated Postman content that the agent is expected to read and could materially influence subsequent actions.