animating-with-code

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

• Third-party content exposure detected (medium risk: 0.30). The workflow requires cloning an external GitHub repository (JohnHeibel/ClaudeAnimationBase) and reading its ANIMATION_GUIDE.md file into the agent's context, exposing the agent to outsider-authored free text from an external repository.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs cloning and installing software from an unofficial third-party GitHub repository (JohnHeibel/ClaudeAnimationBase) at runtime, which is a high-risk operational dependency.