create-qa-test
Warn
Audited by Snyk on Mar 10, 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). When the --explore flag is used the skill "launches qa-tester agent" to navigate an arbitrary provided URL, extract and document page content, and take screenshots (see the "Integration with qa-tester Agent" / "When
--exploreflag is used" sections in SKILL.md), which means untrusted third-party webpages can be read and can materially influence agent behavior.
Audit Metadata