Claudius

hardstop

Hook

Don't let AI destroy your hard work! HardStop is a rock-solid protection for AI-generated commands. Pre-execution safety validation for Claude Code, Claude Cowork. Catches dangerous commands before…

by frmoretto·frmoretto/hardstop·Python·v1.4.9
65· C
Install
git clone https://github.com/frmoretto/hardstop
Stars
30
7d change
Downloads / week
Last active
1mo ago
About

👉 ⭐ Star on GitHub if Hardstop keeps you safe!

Pre-execution safety validation for AI coding agents. Validates every shell command against 428 security patterns before execution — blocking destructive operations, credential theft, infrastructure teardown, and prompt injection. Fail-closed: blocks by default when uncertain.

Ecosystem: The detection patterns are published separately as hardstop-patterns (GitHub) — reusable in any Node.js tool.

Read more on GitHub →
What's inside
6 hookshooks.jsonpattern_loader.pypre_read.pypre_tool_use.pyrisk_scoring.pysession_tracker.py
30-day stars
collecting…
Trust factors
Source
community
Known advisories
0
Maintenance
maintained
License
none
Age
4 months
safetysecurity#pre-execution#agentic-ai#ai-safety#claude-ai#claude-code-hooks#claude-code-plugin#claude-code-plugin-marketplace#claude-code-plugins#claude-code-plugins-marketplace#claude-cowork#cowork#developer-tools#llm#pre-commit-hook#prompt-injection