web-design-guidelines

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

• Third-party content exposure detected (high risk: 0.85). At runtime the skill uses WebFetch to retrieve guidelines from a public GitHub raw URL, so the fetched free-text content is outsider-authored and is ingested into the agent’s LLM context before analysis.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly uses WebFetch at runtime to retrieve and apply the guidelines from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md, and that fetched content contains the rules and output-format instructions which directly control the agent's behavior.