meta-muse-video-analysis

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow takes outsider-authored “analysis prompt” verbatim from user-provided free text (e.g., --prompt/--prompt-file/stdin) and passes it at runtime as input_text in the /responses request to https://api.meta.ai/v1.