expo-react-native-weapon

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

• Third-party content exposure detected (high risk: 0.70). The workflow ingests outsider-authored free text from the operator’s “Input (what the Guardian receives)” block (e.g., arbitrary requirements/copy) into the LLM context; this is user-provided text but it is not authored by the operating user’s organization and is explicitly treated as free-form input to the system at runtime.