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

Ollama ↗

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

Analysis summary

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

Local LLM runtime used by AI agents as a model backend

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.

  • ollama-models-dir global json
    Models directory and runtime configuration
    • win32${USERPROFILE}\.ollama\config.json
    • darwin${HOME}/.ollama/config.json
    • linux${HOME}/.ollama/config.json