deepgram-go-audio-intelligence

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the official Deepgram Go SDK repository on GitHub. This is a legitimate vendor resource used for the intended purpose of the skill.
  • [COMMAND_EXECUTION]: Provides standard commands for setting environment variables and adding additional skills from the vendor using npx. These actions are appropriate for configuring the development environment.
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface:
  • Ingestion points: The skill demonstrates processing external audio data from URLs via the dg.FromURL method.
  • Boundary markers: No delimiters or explicit instructions are provided to help an agent distinguish between transcribed audio content and system instructions.
  • Capability inventory: The skill uses the Deepgram SDK to perform REST API requests for transcription and analysis.
  • Sanitization: The provided examples do not include input validation or filtering of the transcribed text.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 09:56 AM
Security Audit — agent-trust-hub — deepgram-go-audio-intelligence