browse-qa
Warn
Audited by Snyk on Apr 7, 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's Workflow (step 2 "Open/navigate to the target URL" and subsequent snapshot/interaction/console-check steps) explicitly requires loading and interpreting arbitrary third-party webpages and their content, which can materially influence the agent's interactions and pass/fail decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata