manim-composer

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

• Third-party content exposure detected (high risk: 0.90). The skill's required Phase 1 workflow explicitly instructs the agent to "Research the topic" and "Use web search to understand the core concepts" (SKILL.md, Phase 1), meaning the agent will fetch and read untrusted public web content and use it to drive scene-planning decisions—exposing it to indirect prompt injection risk.