browser-verification
Warn
Audited by Snyk on Aug 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). Skill runtime path is browser-controlled session that opens a provided “target URL” and then reads page content via selector checks/console/network/screenshot rendering, so outsider-authored text on that URL (chosen by the outsider) can be ingested by the LLM.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata