assemblyai-transcribe

Warn

Audited by Snyk on Mar 29, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly accepts arbitrary HTTP/HTTPS audio URLs ("Transcribe from a URL" in SKILL.md) and scripts/transcribe.py passes those public URLs (audio_url) to AssemblyAI for transcription, meaning the agent will ingest and interpret untrusted, third-party audio content as part of its runtime workflow.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 29, 2026, 11:46 PM
Issues
1