web-design-guidelines
Warn
Audited by Snyk on Mar 1, 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 and read live guidelines from the public URL https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md using WebFetch, meaning untrusted third-party content is ingested and used to drive rule-checking and output formatting.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The skill fetches runtime rules from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md using WebFetch and directly uses that fetched content to control the agent's review rules and output format, making it a required external source that can alter prompts/instructions.
Audit Metadata