accessibility-auditing
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: 1.00). The skill performs URL-based audits using Playwright MCP (e.g., mcp__playwright__browser_navigate to a provided target URL and snapshot the accessibility tree/screenshots), which lets the agent fetch and read arbitrary public websites supplied by the user, exposing it to untrusted third-party content.
Audit Metadata