skills/deepgram/skills/setup-mcp/Gen Agent Trust Hub

setup-mcp

Pass

Audited by Gen Agent Trust Hub on Oct 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches installation scripts and documentation endpoints from the vendor's official domains, such as deepgram.com and developers.deepgram.com.
  • [REMOTE_CODE_EXECUTION]: Instructions provide commands to download and execute shell and PowerShell scripts directly from the vendor's infrastructure for tool installation (e.g., curl piped to shell for install.sh and Invoke-WebRequest piped to Invoke-Expression for install.ps1).
  • [COMMAND_EXECUTION]: The agent is directed to perform environment discovery by checking for local configuration directories (e.g., .claude, .cursor) and to execute CLI commands for user authentication and status checks (e.g., dg login, dg whoami).
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 3, 2026, 04:17 AM
Security Audit — agent-trust-hub — setup-mcp