apptweak

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

• Third-party content exposure detected (high risk: 0.80). The skill instructs the agent to use the Membrane CLI to run AppTweak actions (see "App -> Review" and the "Running actions" / "Searching for actions" sections) which will fetch app-store data and user-generated reviews from third-party sources, so the agent would read and act on untrusted third-party content.