transcribe

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill interacts with the ElevenLabs API (api.elevenlabs.io) to perform speech-to-text operations, which is a well-known service for this purpose.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it requires the agent to process and refine transcripts generated from untrusted audio or video content.
  • Ingestion points: Untrusted audio/video files are provided via the CLI, and the resulting transcript is refined by the agent as described in SKILL.md.
  • Boundary markers: None identified; the agent is instructed to read the raw text for semantic refinement without delimiters or safety warnings regarding the content.
  • Capability inventory: The script 'scripts/transcribe.ts' has capabilities for file system access (fs.readFileSync, fs.writeFileSync) and network communication (fetch).
  • Sanitization: No validation or sanitization of the transcript content is performed before the agent processes it for refinement.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 12:01 PM