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 workflow (SKILL.md, Phase 1: "Research the topic") explicitly instructs the agent to "Use web search to understand the core concepts" and "Conducts research," meaning it must fetch and interpret open/public web content (potentially user-generated) as part of its planning, which could allow indirect prompt injection to influence decisions and next actions.