aryanbhosale/sh-guard
Semantic shell command safety classifier — AST-based risk scoring for AI coding agents
This tool helps developers who use AI coding agents to prevent dangerous shell commands from being executed accidentally. It takes a shell command proposed by an AI agent and outputs a risk score and explanation, indicating whether the command is safe, a caution, or critical. Developers can use this to automatically block or flag high-risk commands before they cause harm to their systems or data.
Use this if you use AI coding agents like Claude Code, Codex, or Cursor and want an automatic safety net to review and block potentially harmful shell commands they generate.
Not ideal if you manually write all your shell commands and do not use AI coding assistants that generate and execute code on your behalf.
Stars
7
Forks
1
Language
Rust
License
GPL-3.0
Category
Last pushed
Apr 05, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/aryanbhosale/sh-guard"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Windy3f3f3f3f/how-claude-code-works
Deep dive into Claude Code internals — architecture, agent loop, context engineering, and more....
Windy3f3f3f3f/claude-code-from-scratch
🔍 Claude Code 开源了 50 万行代码，读不动？用 ~3000 行 TypeScript 从零复现核心架构，11 章分步教程带你理解 coding agent 精髓。Build...
JCodesMore/ai-website-cloner-template
Clone any website with one command using AI coding agents
repowise-dev/claude-code-prompts
Independently authored prompt templates for AI coding agents — system prompts, tool prompts,...
Enderfga/openclaw-claude-code
OpenClaw plugin — turn Claude Code CLI into a programmable, headless coding engine with plenty...