assemblyai
Warn
Audited by Snyk on Jun 21, 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 can enter the LLM context via AssemblyAI LeMUR when the runtime transcribes outsider-provided audio URLs/files (e.g.,
transcriber.transcribe(audio_source, ...)thentranscript.lemur.*), because the spoken content from that external source becomes readable transcript text that LeMUR feeds into the LLM.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata