assemblyai-transcription

Warn

Audited by Snyk on Jul 11, 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). SKILL.md describes downloading and using AssemblyAI-generated transcript artifacts (e.g., transcript text/JSON, SRT/VTT, summaries) which are outsider-authored speech content from third parties, and those readable transcript fields would be fed into the agent’s LLM context for downstream QA/summarization.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 11, 2026, 01:52 PM
Issues
1
Security Audit — snyk — assemblyai-transcription