Skills
skills/codeboltai/codeboltjs/codebolt-mcp-access/Gen Agent Trust Hub

codebolt-mcp-access

Pass

Audited by Gen Agent Trust Hub on Feb 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The codebolt.terminal namespace provides the execute_command tool, allowing the agent to run arbitrary shell commands for system tasks. Additionally, the codebolt.admin namespace allows creating hooks to execute commands automatically based on project events.
  • [REMOTE_CODE_EXECUTION]: The codebolt.sideExecution namespace includes side_execution_start_code, which enables the execution of inline code strings in a child process.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates downloading resources via git_clone and configuring MCP servers using packages from the NPM registry, such as @modelcontextprotocol/server-filesystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 24, 2026, 06:19 AM