phone-agent
Warn
Audited by Snyk on Jun 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). Outsider free text can enter the LLM context via the Deepgram transcription of the caller’s speech (the caller is not the operating user), which is appended to
conversation_historyand sent asmessagesto OpenAI inscripts/server.py→process_transcript().
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata