browser-qa
Warn
Audited by Snyk on Aug 2, 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.md describes a browser automation workflow that “Navigate[s] to target URL” and then reads page content/errors/network results for the provided URL at runtime, so an outsider can author content in a target page the agent visits (indirect prompt injection via page text).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata