legal-translation
Warn
Audited by Snyk on Jul 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The required workflow ingests the user’s source document text (including any uploaded PDF/DOCX or pasted content) into the LLM context for translation, which is outsider-authored free text whenever the operating user did not author that document; this is an indirect prompt-injection risk via the “Source text” intake path (SKILL.md Step 1 and File Handling).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata