security-skills

andreybuilt/security-skills

★ 0 stars Shell AI/LLM Updated 1d ago

Two skills for reviewing what you are about to trust: an AppSec/CloudSec/CI-CD review pass, and an audit that vets a skill, plugin or MCP server before you install it. 16 fixtures, benign and malicious, and the detector must fire on both.

View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "security-skills": {
      "command": "npx",
      "args": [
        "-y",
        "andreybuilt/security-skills"
      ]
    }
  }
}

README Excerpt

Two Claude Code skills that vet what an agent is asked to trust: the code it reviews, and the instructions it runs under. One zero-dependency scanner you can run on its own, and a test suite that has to prove the scanner fires **and** stays quiet. --- `skill-audit` takes an untrusted instruction bundle, such as a skill, plugin, MCP config or

Topics

ai-agentsappsecclaude-codecloud-securitycode-reviewdevsecopsllm-toolingprompt-injectionsecuritysupply-chain

security-skills

Quick Install

README Excerpt

Topics

Related AI/LLM Servers