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

NanoClaw ↗

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

Analysis summary

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

Lightweight personal AI assistant on the Claude Agent SDK; agents run in Docker containers and reach chat channels, with host mount and sender allowlists under ~/.config/nanoclaw

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.

  • nanoclaw-mount-allowlist global json
    Mount allowlist (host folders agent containers may mount, written by setup)
    • darwin${HOME}/.config/nanoclaw/mount-allowlist.json
    • linux${HOME}/.config/nanoclaw/mount-allowlist.json
  • nanoclaw-sender-allowlist global json
    Sender allowlist (who may message the assistant)
    • darwin${HOME}/.config/nanoclaw/sender-allowlist.json
    • linux${HOME}/.config/nanoclaw/sender-allowlist.json
  • nanoclaw-account global binary
    NanoClaw account record and token (presence only - never read)
    • darwin${HOME}/.config/nanoclaw/account.json
    • linux${HOME}/.config/nanoclaw/account.json