xiaohongshu-images
Warn
Audited by Snyk on Aug 12, 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). The skill ingests user-authored article content (including raw pasted text or file/URL-provided content) and then the LLM parses it to generate HTML (Step 5) and the screenshot script renders that HTML; this means outsider free text is directly consumed at runtime via the user-supplied content input path.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata