qa
Warn
Audited by Snyk on Oct 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The QA skill uses agent-browser to navigate web pages and record evidence, but arbitrary web navigation is classified as low risk rather than medium risk since the agent actively fetches specific URLs rather than monitoring an outsider-submitted feed.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata