web-design-guidelines

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

• Third-party content exposure detected (low risk: 0.10). SKILL.md specifies fetching first-party guidelines text from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md before reviewing user-provided files, but the required runtime workflow does not ingest arbitrary outsider-authored free text without the agent selecting specific items/files.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs fetching runtime guidelines from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md via WebFetch and then applying those fetched rules and output-format instructions to control the agent's behavior, so this URL is a runtime external dependency that directly controls prompts.