web-design-guidelines
Warn
Audited by Snyk on Feb 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md requires fetching and using the latest guidelines from the public URL https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md via WebFetch, meaning the agent will read and act on untrusted, third-party content that can change its behavior.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The skill explicitly fetches runtime instructions from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md which are retrieved at each run and directly control the agent's rules and output format, creating a remote instruction dependency.
Audit Metadata