kling-ai

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly accepts and fetches arbitrary external images via the "image" URL parameter for image-to-video (e.g., generate_video_from_image / animate_portrait) and downloads media from arbitrary URLs (download_media), which ingests untrusted public third‑party content into the agent's workflow.