Skip to content
zero-lab Security Skills

zero-lab Security Skills

by zero-lab
Released
Apache-2.0
Repository Docs
markdown Security

Summary

56 evidence-bound security skills in 10 plugins for authorized assessment, red teaming, detection engineering and AI-agent security.

Features

  • 56 skills across 10 installable plugin bundles
  • Agent, RAG and ML-system security assessments
  • Recon, identity, network, binary and detection-validation coverage
  • Evidence-bound outputs for authorized engagements
  • Works in Claude Code, Codex and any SKILL.md harness

Install This Skill

Add this skill to your favorite AI agent in a few steps.

Any AI agent

This skill is plain instructions — it works with any assistant that accepts custom instructions or system prompts.

  1. Copy the skill content with the button below.
  2. Paste it into your agent's instruction file or system prompt (for example AGENTS.md, .cursorrules, or a custom instructions field).
  3. Ask the agent to apply the skill whenever the task matches.

Skill Content

Markdown Content

Copy this content and use it with your preferred AI agent

# zero-lab Security Skills

56 skills in 10 plugins for authorized security assessment.

## Install

Claude Code:

```text
/plugin marketplace add zero-lab-ai/skills
/plugin menu
```

Other harnesses:

```sh
npx skills add zero-lab-ai/skills
```

For authorized use only; the skills do not grant permission or expand scope.

Full skill definitions: https://github.com/zero-lab-ai/skills

Usage Instructions

Learn how to use this skill with different AI agents.

Generic Instructions
npx skills add zero-lab-ai/skills

Description

zero-lab skills is a collection of 56 agent skills from zero-lab.ai, grouped into ten installable plugins: agent-security, recon-operations, identity-security, application-endpoint-security, network-protocol-security, binary-forensics, detection-validation, engagement-operations, rag-security and ml-system-security. Each skill is a self-contained SKILL.md folder, so you can install a whole bundle or copy a single skill into any harness that reads the format.

The set is written for authorized work only and says so up front: the skills do not grant permission or widen scope, and those that touch adversary behaviour are designed to measure exposure, preserve evidence and hand findings back to defenders. Highlights include agent-surface-audit and prompt-injection-assessment for reviewing agent tools and instruction channels, agent-runtime-validation using benign sentinels, network-recon and osint-scanner for scoped reconnaissance, plus bundles for retrieval (RAG) and ML system security and for planning, evidence and report assembly in an engagement.

Install in Claude Code with /plugin marketplace add zero-lab-ai/skills, in Codex with codex plugin marketplace add zero-lab-ai/skills, or with npx skills add zero-lab-ai/skills for other harnesses. Apache-2.0 licensed.

Install

Related Skills

Skill: Firebase Security Rules Auditor

by Firebase

Firebase's official red-team skill for auditing Firestore and Cloud Storage security rules — hunting privilege escalation, create/update bypasses and resource-exhaustion holes.

Security

Skill: Auth0 Agent Skill

by Auth0

Featured

Auth0's official agent skill: a router that detects your framework and intent, then loads the right Auth0 guidance for login, MFA, Organizations, tenant audits, debugging or provider migration.

DevelopmentSecurity
Browse all skills →