soia-pkm-clip-rednote
Warn
Audited by Snyk on Jul 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). Yes—this skill fetches outsider-authored free text from public Xiaohongshu pages at runtime (HTML containing
window.__INITIAL_STATE__), then parses and inserts the extracteddesc/title/author/tag strings into the generated Markdown/AI-reply context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata