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 explicitly instructs the agent to "Fetch the latest guidelines" using WebFetch from the public URL https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md (see "Guidelines Source" / "How It Works"), so the skill ingests untrusted third-party content that the agent must read and act on, which could modify its actions or outputs.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill fetches runtime guidelines from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md and uses the fetched rules and output-format instructions to directly control the agent's prompts and behavior, making this a required remote dependency.