lovstudio-translation-review
Warn
Audited by Snyk on Jul 29, 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 instructs the agent to read the user-provided Chinese source document and English translation files (including extracting text from user-uploaded .docx via pandoc), meaning outsider-authored free text is ingested directly for review.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata