Skip to content
Back to skills

Security Review

ASecurity

Review the code in a pull request for security problems it introduces — the highest-risk findings first.

  • 13 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added October 9, 2026
developmentrustshellsqlsecurity

Works with

  • cli

Security analysis

A100/100

Scanned October 9, 2026

npx -y skills add novibe-org/novibe --skill security-review --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Security Review?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Security Review
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/novibe-org-security-review/badge)](https://www.skillsdirectory.com/skills/novibe-org-security-review)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: security-review
description: Review the code in a pull request for security problems it introduces — the highest-risk findings first.
---

# Security review

Read the changed code, and follow untrusted input from where it enters — a request, a file, a
message, an environment variable, another service's response — to everywhere it is used. Flag
what makes the system exploitable:

- **injection** — input reaching SQL, a shell, a template, a path, a URL fetched server-side, or a
  deserializer
- **access** — an entry point with no authentication or authorization check, or a check a caller
  can bypass
- **isolation** — one user's or tenant's data reachable by another
- **exposure** — secrets, tokens or personal data in logs, errors, responses or the client
- **unsafe defaults** — permissive CORS, cookies without `Secure`/`HttpOnly`, disabled TLS
  verification, weak or home-made cryptography

For each finding: the file and line, how an attacker would exploit it, and the fix. Highest risk
first; leave out what is not exploitable.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.