AI tool official cli
Risk level
low
10/100

mini-swe-agent ↗

mini-swe-agent is an officially published AI tool from SWE-agent (community). Anomity scores its risk at 10 out of 100 (low).

Analysis summary

mini-swe-agent is an officially published AI tool from SWE-agent (community). Anomity scores its risk at 10 out of 100 (low).

Minimal bash-only coding agent from the SWE-agent team, run as the mini CLI with any LiteLLM model

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.

  • mini-swe-agent-env global binary
    Global .env with the model name and provider API keys (presence only - never read)
    • win32${LOCALAPPDATA}\mini-swe-agent\mini-swe-agent\.env
    • darwin${HOME}/Library/Application Support/mini-swe-agent/.env
    • linux${HOME}/.config/mini-swe-agent/.env
  • mini-swe-agent-last-run global binary
    Trajectory of the last mini run (presence only - holds conversation content)
    • win32${LOCALAPPDATA}\mini-swe-agent\mini-swe-agent\last_mini_run.traj.json
    • darwin${HOME}/Library/Application Support/mini-swe-agent/last_mini_run.traj.json
    • linux${HOME}/.config/mini-swe-agent/last_mini_run.traj.json

Known vulnerabilities in mini-swe-agent

Public CVEs and advisories that name mini-swe-agent as the affected component, newest first.

Find every machine running mini-swe-agent with Anomity →