post-content

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

• Third-party content exposure detected (medium risk: 0.30). In the posting workflow, the agent ingests user-picked or user-supplied Drive asset content (via /scan-assets queue selection and then the caption engine called with the picked Drive file/id in /script/references/shared/captions.md), and that free-form media-derived transcript/captions are then used to build and publish/schedule posts.