NSFW Video Generation

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt's numerous curl examples instruct embedding an Authorization: Bearer YOUR_API_KEY header (i.e., placing API keys directly in commands), which requires the model/user to place secret tokens verbatim into generated requests/outputs and is a high-risk credential-exposure pattern.

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly accepts arbitrary image URLs in the "Image-to-Video Animation" flow (see the image_urls parameter and example request in SKILL.md), meaning it fetches and ingests untrusted public content that the agent must interpret and that directly influences generation behavior.