bmad-review

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

• Third-party content exposure detected (medium risk: 0.30). Runtime path: the skill ingests caller-provided content (diff/file/pasted text) via “Load the content” and then runs lenses (including edge-case-hunter and adversarial) that read that staged file, so outsider-authored free text is directly processed at runtime.