sec-unit
CommunityGuard Bash commands from untrusted output.
Authoraldengolab
Version1.0.0
Installs0
System Documentation
What problem does it solve?
A five-point security checklist helps ensure you don't construct dangerous Bash commands when results come from kubectl, argocd, helm, WebFetch, or git log. It prevents prompt-injection, data leakage, and misconstructed pipelines by requiring explicit authorization before actions.
Core Features & Use Cases
- Applies the sec-unit checklist automatically to external outputs before command construction.
- Detects common risk vectors like instruction-in-data positions, URL-path substitutions, multi-step exfiltration risk, and inline executions.
- Works as a gating layer for Claude Code workflows, ensuring safe automation of infrastructure tasks.
Quick Start
Ask sec-unit to run the five-point security checklist immediately after receiving external output and before composing any Bash command.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: sec-unit Download link: https://github.com/aldengolab/lorist/archive/main.zip#sec-unit Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.