korean-product-detail-page
Warn
Audited by Snyk on May 2, 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 explicitly requires researching and ingesting public Korean sources and user-supplied product/reference URLs—using a "lightweight Chrome DevTools/CDP-first" link-research flow described in references/browser-link-research.ko.md and the SKILL.md/workflow—so the agent will fetch and interpret untrusted third-party page content that can materially influence copy, image-generation prompts, and next actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata