AIzilla CAGE · Risky Command Guard - Check AI Agent Commands
Pricing
from $5.00 / 1,000 command checks
AIzilla CAGE · Risky Command Guard - Check AI Agent Commands
Give shell commands an AI agent wants to run and get a risk level for each: read-only, local change, sensitive (network, sudo, secrets) or irreversible (delete, overwrite, force-push), with reasons. Nothing is executed.
Pricing
from $5.00 / 1,000 command checks
Rating
0.0
(0)
Developer
KOTARO project
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
3 days ago
Last modified
Categories
Security
Limited permissionsShare
🛡️ Risky Command Guard — check shell commands before an AI agent runs them
AI coding agents (Claude Code, Cursor, Copilot agents, Devin-style bots, your own LangChain/MCP tools) can type shell commands on your machine or server. One wrong line — rm -rf, git push --force, curl … | bash, DROP TABLE — and the damage cannot be undone.
Risky Command Guard reads the command first and tells you how dangerous it is. It never executes anything.
What you get for every command
| Field | Meaning |
|---|---|
level / levelName | 0 read_only · 1 local_change · 2 sensitive · 3 irreversible |
allow | true for read-only commands — safe to run |
askFirst | true for local changes and sensitive commands — ask a human first |
block | true for irreversible commands — do not run |
reasons | Plain-English reasons, e.g. "recursive delete", "git push --force rewrites remote history", "runs a script downloaded from the network" |
A command line with &&, ; or | is as risky as its riskiest part. Commands hidden inside $( … ), backticks, bash -c '…', python -c '…' or wrappers such as env, timeout, nice and sudo are checked too.
What it catches
- 🗑️ Irreversible: deletes, overwrites with
>,find -delete,dd of=,git reset --hard,git clean -f, force-push,rsync --delete,DROP TABLE,DELETE/UPDATEwithoutWHERE, cloud bucket deletes, shutdown, fork bombs - 🌐 Sensitive: sending data out (
curl -X POST,scp,ssh,git push,npm publish),sudo, reading secret files or$…TOKENvariables, killing processes,eval/bash -c - 🔧 Local change: installing packages, editing files, commits, downloads
Input
Or paste many commands in text, one per line.
Output example
Use it as a guard
Call this Actor (or its API) from your agent before every shell command:
allow → run · askFirst → ask the user · block → refuse.
Pricing
Pay per checked command (see the Pricing tab). Apart from Apify's standard start fee, there is no per-run charge.
Notes
- The check is rule-based and conservative: an unknown command is treated as a local change. It is a safety net, not a guarantee — keep backups and human review for production systems.
- Commands are only read as text. Nothing is executed, stored outside your run, or sent anywhere.
Part of AIzilla CAGE — guardrail systems for AI coding agents that run on your own machine: https://aizilla.neuro-hive.jp/en/
Made by KOTARO Data Works 🇯🇵
