AI tool official cli
Risk level
low
10/100

FrontierAgent ↗

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

Analysis summary

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

Open-source terminal agent for long-horizon research and file-based work, with single-agent and agent-team workflows (frontier-agent)

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.

  • frontier-agent-settings global json
    User settings, including auto-approve and plan mode (settings.json)
    • darwin${HOME}/.config/apodex/settings.json
    • linux${HOME}/.config/apodex/settings.json
  • frontier-agent-env global binary
    Provider API keys and endpoints env file (presence only - never read)
    • darwin${HOME}/.config/apodex/env
    • linux${HOME}/.config/apodex/env