web-design-guidelines

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs the agent to fetch and use live guidelines from a public GitHub URL (https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md), requiring the agent to read and apply those externally-hosted rules which can alter its actions and output format.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill instructs the agent to fetch and use live rules/instructions from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md at runtime, meaning remotely-hosted content directly controls the agent's prompts/behavior and is required for operation.