web-design-guidelines

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow and Step 1 explicitly require using WebFetch to retrieve and parse the public GitHub raw URL https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md and then apply those fetched rules to drive review decisions, so arbitrary content at that third-party URL could materially influence the agent's actions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill requires fetching live rules from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md at runtime, and those fetched guidelines directly control the agent's instructions/output format and are a required dependency for each review.