google-gemini-media

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly ingests and analyzes public, user-generated content (e.g., "Direct YouTube URL" in SKILL.md section 8.1 and the Video Understanding examples), and those analyzed outputs (summaries, timestamps, storyboards) are used to drive downstream actions like TTS and generation, allowing untrusted third-party content to influence agent behavior.