full-workflow
Warn
Audited by Snyk on Feb 26, 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 workflow explicitly uses the mcp-client Playwright browser_run_code calls in Phase 1 and Phase 1.5 to navigate and scrape arbitrary user-supplied websites (e.g., "Navigate to homepage", examples calling browser_run_code) and captures untrusted site text/error messages which are then used to drive test assertions and subsequent automation decisions.
Audit Metadata