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
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 2, 2026, 05:51 AM
Issues
1