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

Omnigent ↗

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

Analysis summary

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

Open-source AI agent meta-harness that orchestrates Claude Code, Codex, Cursor, Pi, and custom ACP agents with policies and sandboxing

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.

  • omnigent-user-config global yaml
    User YAML configuration (harnesses, ACP agents, overrides)
    • win32${USERPROFILE}\.omnigent\config.yaml
    • darwin${HOME}/.omnigent/config.yaml
    • linux${HOME}/.omnigent/config.yaml
  • omnigent-project-config project yaml
    Project YAML configuration (overrides user config)
    • win32${PROJECT}\.omnigent\config.yaml
    • darwin${PROJECT}/.omnigent/config.yaml
    • linux${PROJECT}/.omnigent/config.yaml

Known vulnerabilities in Omnigent

Public CVEs and advisories that name Omnigent as the affected component, newest first.

Find every machine running Omnigent with Anomity →