tidas-bilingual-transcreation
Warn
Audited by Snyk on Jul 23, 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 outsider-authored free text at runtime from
--input /abs/path/rows/processes.jsonland other “source rows”/evidence fields (outsider dataset content not authored by the operating user), which the LLM reads during the Codex “review” step to generatetrans-reviewed.jsonl.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata