compatibility-testing
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 SKILL.md explicitly shows agents and Playwright tests navigating to arbitrary URLs (e.g., page.goto('https://example.com') in "Responsive Design Testing" and the Agent-Driven "Task" with a url parameter, plus metadata.targetUrl in schemas), so the agent fetches and interprets public website content which is untrusted and can influence testing actions.
Audit Metadata