css-animation-skill

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

• Third-party content exposure detected (low risk: 0.10). The workflow involves researching a live app via browser extraction using Claude-in-Chrome MCP, exposing the agent to potentially arbitrary web content.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs installation of external content from an individual GitHub repository via npx, introducing an unverified third-party runtime operational dependency.