web-design-guidelines

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md:13-16 requires runtime fetching of guidelines from a public URL (https://raw.githubusercontent.com/.../command.md) and then using the fetched text to drive rule checking, which feeds outsider-authored free text into the LLM context.

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

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