deepgram-setup-mcp

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the Deepgram CLI using pipx install deepctl or pip install --upgrade deepctl. These are standard installation procedures for the official Deepgram command-line utility.
  • [COMMAND_EXECUTION]: The skill configures the agent to execute dg mcp as a local MCP server, providing transcription, text-to-speech, and project management capabilities through the CLI.
  • [INDIRECT_PROMPT_INJECTION]: The skill creates a potential surface for indirect prompt injection by connecting the agent to an external documentation service.
  • Ingestion points: The agent receives content from the hosted documentation MCP at https://api.dx.deepgram.com/kapa/mcp or via transcription results from the local CLI.
  • Boundary markers: None explicitly defined in the setup instructions; reliance is placed on the agent's internal safety filters for external content.
  • Capability inventory: The skill has the capability to write to local configuration files (e.g., .cursor/mcp.json, .windsurf/mcp.json) and execute the dg CLI tool.
  • Sanitization: No specific sanitization or filtering of the remote documentation content is implemented within the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 06:55 AM
Security Audit — agent-trust-hub — deepgram-setup-mcp