AI tool official ai-agent
Risk level
low
10/100

OpenClaw ↗

OpenClaw is an officially published AI tool from OpenClaw. Anomity scores its risk at 10 out of 100 (low).

Analysis summary

OpenClaw is an officially published AI tool from OpenClaw. Anomity scores its risk at 10 out of 100 (low).

Open-source local AI assistant with full host access, MCP servers, skills, and chat-app control channels

Why this entry scored 10 out of 100

This profile starts at the catalog's neutral base of 50. Because the entry is officially published, trust adjusts the score by -40. The entry declares no high-risk capabilities on its own, so capabilities add nothing. It matches no dangerous capability combinations. The clamped result is 10, placing it in the low band.

See the full scoring formula →

Findings

  • Published by the vendor Trust offset
    Contribution to score: -40

Configuration surface

Files this AI tool reads on the host. Anything written here changes what the agent does next.

  • openclaw-global-config global json
    Main OpenClaw config: MCP servers, model providers, agents, and chat-app channels
    • darwin${HOME}/.openclaw/openclaw.json
    • linux${HOME}/.openclaw/openclaw.json
    • win32${USERPROFILE}\.openclaw\openclaw.json
  • openclaw-user-skill global markdown-frontmatter
    OpenClaw skills (user-scope)
  • openclaw-workspace-skill global markdown-frontmatter
    Per-agent workspace skills (incl. org-custom)