design-md-validator

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime path can fetch a user-supplied raw DESIGN.md URL via curl -sL <url> > /tmp/DESIGN.md and then runs npx @google/design.md lint /tmp/DESIGN.md, so the LLM context may include outsider-authored free text from that fetched page/file (public web content).