generate-video

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

• Third-party content exposure detected (high risk: 0.70). The skill's mandatory /generate-video flow (SKILL.md Steps 2.5 and 3) calls the image generation and quality-check pipeline (references/image-generator.md and references/image-quality-check.md) which sends prompts to external APIs (Nano Banana Pro / Gemini) and explicitly uses Claude (an external third‑party LLM) to evaluate results and produce "improvement" prompts that the agent consumes to decide re-generation and next actions, so untrusted third‑party content can directly influence tool use.