web-design-guidelines-6
Warn
Audited by Snyk on Feb 18, 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). This skill instructs the agent to fetch and read live guidelines from a public third-party URL (https://raw.githubusercontent.com/cloudflare/web-interface-guidelines/main/command.md), so it ingests untrusted external content at runtime that could contain injected instructions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs fetching runtime rules and output-format instructions from https://raw.githubusercontent.com/cloudflare/web-interface-guidelines/main/command.md using WebFetch, so external content directly controls the agent's prompts/behavior and is a required dependency.
Audit Metadata