transcribe-podcast

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs legitimate transcription and text processing tasks without malicious intent.
  • [EXTERNAL_DOWNLOADS]: Utilizes external APIs from AssemblyAI and Google (Gemini) to perform audio-to-text transcription.
  • [COMMAND_EXECUTION]: Orchestrates functionality by invoking internal or specialized skills such as transcribe-assemblyai and transcribe-gemini-raw.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes transcription data derived from external audio files. While this creates an ingestion point for untrusted data, the specific instructions to format the text without reordering or paraphrasing reduce the likelihood of the agent executing embedded commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 10:33 PM
Security Audit — agent-trust-hub — transcribe-podcast