AI tool official desktop-app
Risk level
low
10/100

Continuum ↗

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

Analysis summary

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

Local-first workbench and CLI for running Claude Code, Codex, Cursor, Antigravity, Grok, and OpenCode sessions across Mac, Windows, and Linux

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.

  • continuum-app global plist
    Installed Continuum.app (presence)
    • darwin/Applications/Continuum.app/Contents/Info.plist
  • continuum-analytics-cache global json
    Mac app analytics cache (Clawdmeter data dir)
    • darwin${HOME}/Library/Application Support/Clawdmeter/analytics-cache.json
  • continuum-cli-config global json
    CLI connection profiles (host/port/provider defaults; no tokens)
    • win32${APPDATA}\continuum\config.json
    • darwin${HOME}/Library/Application Support/continuum/config.json
    • linux${HOME}/.config/continuum/config.json
  • continuum-desktop-agent-token global binary
    Windows/Linux desktop bundled-daemon bearer token
    • win32${APPDATA}\Continuum\agent\agent-token
    • linux${HOME}/.config/Continuum/agent/agent-token