narova-openai
Warn
Audited by Snyk on Aug 22, 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 runtime worker (
tool/worker.py) ingests outsider-authored free text via thesynthesizeprotocol request fields (textandoptions.instructions) from JSONL onsys.stdin, then maps that text into an OpenAI TTS call without selecting a specific pre-identified item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata