Skills
skills/qwibitai/nanoclaw/add-atomic-chat-tool/Gen Agent Trust Hub

add-atomic-chat-tool

Pass

Audited by Gen Agent Trust Hub on Apr 26, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The installation process requires running build and management commands (pnpm, tsc, launchctl) to integrate the new MCP server into the agent runner.
  • [EXTERNAL_DOWNLOADS]: The documentation points to the official GitHub repository for Atomic Chat (AtomicBot-ai/Atomic-Chat) for downloading the prerequisite desktop application.
  • [DATA_EXFILTRATION]: The skill facilitates sending prompts to a local API endpoint (defaulting to host.docker.internal:1337). This is the intended behavior for local model inference and does not involve sending data to unauthorized external domains.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 26, 2026, 09:50 PM