AI tool official cli
Risk level
low
10/100

LLM ↗

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

Analysis summary

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

Command-line tool and Python library for prompting OpenAI, Anthropic, Gemini and local models, with tool calling, templates and a plugin ecosystem (llm)

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.

  • llm-cli-keys global binary
    Stored provider API keys (presence only - never read)
    • win32${APPDATA}\io.datasette.llm\keys.json
    • darwin${HOME}/Library/Application Support/io.datasette.llm/keys.json
    • linux${HOME}/.config/io.datasette.llm/keys.json
  • llm-cli-logs global binary
    Prompt and response log database (presence only - holds conversation content)
    • win32${APPDATA}\io.datasette.llm\logs.db
    • darwin${HOME}/Library/Application Support/io.datasette.llm/logs.db
    • linux${HOME}/.config/io.datasette.llm/logs.db
  • llm-cli-aliases global json
    Model aliases
    • win32${APPDATA}\io.datasette.llm\aliases.json
    • darwin${HOME}/Library/Application Support/io.datasette.llm/aliases.json
    • linux${HOME}/.config/io.datasette.llm/aliases.json