ctrlrun

Name: ctrlrun Review
Item: ctrlrun
Rating: 2.8
Author: Aaron Matthews

Skill Development Usable

Works inClaude Code

Usable Scanned — metadata only

Reduces risk of unintended code execution and data exfiltration when delegating tasks to AI agents.

The execution safety layer for AI agents.

Prevent AI agents from executing dangerous system commands without human approval
Monitor and log all code execution attempts for security audits and compliance
Set execution boundaries so agents can only run whitelisted scripts or functions

27 starsApache-2.0 (commercial OK)FreeQuick setup

Usable rating — This tool is functional but has notable gaps. Review the evaluation notes below before deploying.

Why it matters

Reduces risk of unintended code execution and data exfiltration when delegating tasks to AI agents. Enforces sandboxed execution boundaries, protecting infrastructure from agent mistakes or prompt injection attacks.

Best for

Engineering teams deploying AI agents in production environments requiring controlled execution and audit trails.

Works in

Claude Code Claude Cowork Claude Chat

Source

https://github.com/CTRLRun/ctrlrun

By CTRLRun

How to Get It

Option 1: Claude Desktop App (Code Mode)Click the + button next to the prompt box → Plugins → Add plugin. Search and click Install. Skills work in Claude Code only.

Option 2: Paste into Claude CodeCopy the command below and paste it into your conversation. Claude will install it.

Command

claude plugins install CTRLRun/ctrlrun

Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.

Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.

First thing to try

After installing, paste this into Claude:

Help me prevent AI agents from executing dangerous system commands without human approval

CostFree

Trust Signals Auto-scanned

Stars27Contributors4Last updated2026-10-26LicenseApache-2.0 (OK for commercial use)Known CVEsNone foundSources: GitHub Advisory Database + OSV.dev · Scanned 2026-10-28 · scanner v1

Community Pulse Growing

Discussed on Hacker News

Show HN: An open source safety layer for AI agent actions — Hacker News · 4 pts
Control AI agents at the execution layer, not the prompt — Hacker News · 1 pts

2 mentions across 1 sources

Reviewer notes

Auto-scanned review. These are observations, not a security certification.

Scored from trust signals (evidence-eval-v1): 26 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.

Things to check

Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.

How to evaluate tools before deploying →

Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.

Evaluation Scores

Evaluation

Ease of Use

3/5

Versatility

2/5

Reliability

3/5

Security

3/5

Overall score2.75 / 5.00 UsableEvaluatedOct 2026

Scored from trust signals (evidence-eval-v1): 26 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.

← Back to the Claude Observatory