web-design-guidelines
Warn
Audited by Snyk on Mar 5, 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 explicitly instructs the agent to fetch live guidelines from a public URL (https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md) via WebFetch before each review, and then to read and apply those fetched rules to decide checks and output format, which lets untrusted third-party content materially influence agent behavior.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs at runtime to fetch and "Use WebFetch" to load rules and output-format instructions from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md, which directly controls agent prompts/behavior and is required for the skill to run.
Audit Metadata