Create GitHub README
Warn
Audited by Snyk on Feb 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill explicitly navigates to and ingests content from user-provided or auto-detected live demo URLs (via Playwright MCP when a URL is found in user input, package.json homepage, Vercel/GitHub Pages, or any URL in an existing README.md) and reads/parses existing README contents—both are arbitrary public/web sources that the agent consumes and that can affect whether it captures screenshots and how it generates/updates the README, creating a channel for indirect prompt injection.
Audit Metadata