design-system-analyzer
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly navigates to arbitrary target URLs (mcp__chrome-devtools__navigate_page in SKILL.md/Workflow) and runs extraction scripts that read document.body, document.styleSheets, and querySelector results (references/analysis-guide.md), so it ingests and interprets untrusted public website content and could be exposed to indirect prompt injection.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill runtime navigates to a user-supplied site via mcp__chrome-devtools__navigate_page (url: "") and runs in-page evaluation scripts that extract and inject the site's CSS/JS-derived data into the generated system prompt, so a malicious external page could directly influence prompts or cause remote code execution in the page context.
Audit Metadata