translate
Warn
Audited by Snyk on Jun 22, 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). Outsider free text is the user-provided source document itself (Markdown/plain text) which the workflow reads and passes into the LLM for translation (Phase 1 read-through → Phase 2 sub-agent/source segment prompts), so the LLM context can include arbitrary outsider-authored prose.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata