web-design-guidelines-7
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). The skill instructs the agent to fetch and apply rules from a public raw GitHub URL (https://raw.githubusercontent.com/railwayapp/web-interface-guidelines/main/command.md) via WebFetch, meaning it will read and act on untrusted third-party content and could be subject to indirect prompt injection.
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/railwayapp/web-interface-guidelines/main/command.md, meaning externally fetched content directly controls the agent's prompts/behavior and is required for operation.
Audit Metadata