web-design-guidelines

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

• Third-party content exposure detected (high risk: 0.95). The skill’s required workflow fetches public web content at runtime from the specified URL (raw.githubusercontent.com) and then ingests that fetched free-text “guidelines” into the agent’s LLM context to drive the review, which is an outsider-authored source.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill fetches runtime instructions from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md and uses that fetched content to control its checking rules and output format, so the external URL directly controls agent behavior.