css-animation-skill

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

• Third-party content exposure detected (high risk: 0.75). The required workflow invokes a “scrapes your live app using Claude-in-Chrome MCP” step, which ingests readable page/app content at runtime (outsider-authored free text in the sense of arbitrary web/app DOM/text not authored by the operating user), creating an indirect prompt-injection risk.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs the agent at runtime to run the installer (e.g., "npx skills add neonwatty/css-animation-skill" which pulls code from https://github.com/neonwatty/css-animation-skill), so remote code would be fetched and executed and would control the skill's behavior.