elevenlabs-remotion

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

• Third-party content exposure detected (high risk: 0.90). This skill's CLAUDE.md explicitly says that "If user provides a website URL, WebFetch the URL" to extract colors, typography, logo and other design tokens—meaning the agent will fetch and parse arbitrary public websites (untrusted third‑party content) as part of its workflow.