mcp-server-code-execution-mode

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for installing prerequisites using system package managers (brew, apt, dnf) and setting up container runtimes (podman, docker).
  • [EXTERNAL_DOWNLOADS]: Downloads the bridge tool via pip or uv and pulls a container image from GitHub Container Registry (ghcr.io/elusznik/mcp-code-execution:latest). These are official distribution channels for the project.
  • [DYNAMIC_EXECUTION]: The core functionality of the skill is to provide a run_python tool. This is the intended purpose of the skill—enabling the AI to write and execute code within a sandboxed environment to interact with MCP servers. The skill explicitly mentions security controls such as rootless containers, no network access, and read-only filesystems for the sandbox environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 10:42 PM
Security Audit — agent-trust-hub — mcp-server-code-execution-mode