security-review

Identify exploitable security vulnerabilities in code and report prioritized findings in Markdown and JSON.

Updated Mar 16, 2026
One-click install
npx skills add https://github.com/liminal-ai/code-steward --skill security-review-liminal-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: security-review
Source: https://github.com/liminal-ai/code-steward/tree/main/.claude/plugins/code-steward-reviews/skills/security-review
Command: npx skills add https://github.com/liminal-ai/code-steward --skill security-review-liminal-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Identify exploitable security vulnerabilities in code by thinking like an attacker and reporting concrete findings to enable faster remediation and risk reduction.

Core Features & Use Cases

  • The skill guides security reviews by analyzing code changes, PRs, and audit tasks to surface actionable vulnerabilities.
  • It supports threat modeling, OWASP top 10 checks, and reproducible security reports for developers and security teams.
  • Use Case: When a PR touches authentication or data handling, run this review to generate structured findings and recommended fixes.

Quick Start

Review the latest code changes, identify exploitable vulnerabilities, and produce a structured security report.

Frequently Asked Questions about security-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I identify exploitable security vulnerabilities in a pull request?

Run an attacker-grade security review on your pull request to identify exploitable vulnerabilities and generate a structured findings report. This surfaces actionable flaws in code changes touching authentication or data handling.

What is threat modeling and OWASP top 10 checking for code changes?

Threat modeling and OWASP top 10 checking for code changes is a security review process that analyzes code for exploitable attack vectors. It outputs prioritized findings with severities and CWE mappings.

How do I generate a structured security audit report with CWE mappings?

Generate a structured security audit report by running an attacker-grade code review across your languages and frameworks. It outputs prioritized findings with CWE mappings and remediation recommendations in Markdown and JSON formats.

Can I run security reviews across multiple programming languages and frameworks?

Yes, you can run security reviews across multiple programming languages and frameworks. The review applies threat modeling and attacker-grade analysis to code changes and audit tasks regardless of the specific tech stack.

What's the best way to automate code security reviews for risk management?

Automate code security reviews for risk management by analyzing PRs with security implications to produce reproducible reports. This approach yields prioritized findings and remediation recommendations to reduce risk.

Does the security review output include remediation recommendations for developers?

Yes, the security review output includes remediation recommendations for developers. It delivers a prioritized findings report in Markdown and JSON formats containing severities, CWE mappings, and concrete fixes.