AI tool official cli
Risk level
low
10/100

CritiqueCode ↗

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

Analysis summary

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

Author coding agent with forced review and verified repair (critique-code / @critiquedotsh/harness)

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.

  • critique-code-auth global binary
    Stored machine/API credentials (presence only — never read)
    • win32${USERPROFILE}\.critique\code\auth.json
    • darwin${HOME}/.critique/code/auth.json
    • linux${HOME}/.critique/code/auth.json
  • critique-code-settings global json
    CritiqueCode settings (model route, author and review models, shell approval mode)
    • win32${USERPROFILE}\.critique\code\settings.json
    • darwin${HOME}/.critique/code/settings.json
    • linux${HOME}/.critique/code/settings.json
  • critique-code-user-skill global markdown-frontmatter
    User-scope CritiqueCode skills
  • critique-code-project-skill project markdown-frontmatter
    Project-scope Critique skills (.critique/skills)