test-exploratory
Warn
Audited by Snyk on Oct 7, 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 skill instructs the agent to perform exploratory QA by browsing a live application, where the agent interacts with UI elements and pages that may contain outsider-authored text (such as user comments, profile details, or posts), but the application pages themselves are dynamically loaded target URLs rather than monitored feeds/inboxes or external issue trackers.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata