Cloudflare
Warn
Audited by Snyk on Mar 5, 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 Troubleshoot workflow (Workflows/Troubleshoot.md) explicitly instructs the agent to fetch deployment logs from the Cloudflare API and to use Chrome MCP to navigate to the deployed site's URL (deployment.url) and read console/network/visual output—i.e., ingesting and acting on arbitrary public/site content that can materially influence actions.
Audit Metadata