Safe Bash
- Updated February 1, 2026
- Virtue-AI/cowork-virtueai-plugin
safe-bash is a Claude Code skill in the AI & Agent Building category. Detects and blocks dangerous Bash commands before execution using pattern matching and AI-powered analysis
Key points
- safe-bash
- AI & Agent Building
- AI-coding skill
Safe Bash by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
/plugin marketplace add Virtue-AI/cowork-virtueai-plugin/plugin install safe-bash@virtue-ai-pluginsAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Last updated | February 1, 2026 |
|---|---|
| Repository | Virtue-AI/cowork-virtueai-plugin ↗ |
What it does
Detects and blocks dangerous Bash commands before execution using pattern matching and AI-powered analysis
README.md
Virtue-AI Plugins for Claude Code / Cowork
A collection of plugins for Claude Code and Cowork.
Available Plugins
| Plugin | Description |
|---|---|
| safe-bash | Detects and blocks dangerous Bash commands before execution using pattern matching and AI-powered analysis |
Installation
# Step 1: Add the marketplace
/plugin marketplace add Virtue-AI/cowork-virtueai-plugin
# Step 2: Install a plugin
/plugin install safe-bash
Or use the interactive UI:
- Run
/pluginin Claude Code or Cowork - Go to Marketplaces tab → Add
Virtue-AI/cowork-virtueai-plugin - Go to Discover tab → Find and install plugins
Plugins
safe-bash
Protects your system by intercepting Bash commands before execution.
Features:
- Pattern Matching: Blocks known dangerous commands (
rm -rf /,mkfs,dd, etc.) - AI Detection (Optional): Uses GPT-4o-mini to analyze commands when
OPENAI_API_KEYis set
Configuration:
# Enable AI-powered detection (optional)
export OPENAI_API_KEY='your-api-key'
References
License
MIT
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10AI & Agent Buildingagents