ai-multimodal

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

• Third-party content exposure detected (high risk: 0.90). The skill's reference documentation (e.g., references/video-analysis.md and references/vision-understanding.md) explicitly shows ingesting public URLs and YouTube videos via types.Part.from_uri and then transcribing/summarizing/analyzing them, so the agent is expected to read untrusted, user-generated third‑party content that can materially influence its outputs and follow-up actions.