web-design-guidelines
Warn
Audited by Snyk on Feb 28, 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 explicitly instructs the agent to fetch and read guidelines from a public upstream URL (https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md) or via WebFetch/curl and then apply those rules to decide actions, so it clearly ingests untrusted third‑party content that can influence behavior.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill, when run locally, fetches runtime guidance from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md and reads/applies that content as the rules that control the agent's review behavior, making it a required external dependency.
Audit Metadata