Skip to main content
skill CX Codex

secure-code-review · securityskills — Claude Code skill for vulnerability checks

secure-code-review — a skill that audits code for vulnerabilities using vulnerability-class checklists — traces inputs to SQL and commands, checks access control and trust boundaries.

no license 1,900 installs updated 2026-08-26

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add securityskills/skills --skill secure-code-review -a claude-code
Open on GitHub

What secure-code-review does

The skill teaches the agent to find vulnerabilities structurally, not line-by-line. First, it identifies entry points, trust boundaries, data stores, and privileged operations. Then it traces untrusted data to SQL, command shells, HTML rendering, file paths, deserialization, and redirects — checking for parameterized queries, escaping, path validation.

For authorization, it verifies that each endpoint filters queries by the caller's user or tenant ID, rotates sessions, and sets secure cookie flags. For cryptography, it confirms the use of library primitives instead of hand-rolled implementations and random numbers from CSPRNG. The agent reports findings with severity, exploitation path, and a suggested fix.

Install via npx skills add in Claude Code, Codex, Cursor, OpenCode, and Gemini CLI; in GitHub Copilot via gh skill install.

What it helps with

  • audit a PR or codebase for SQL injection and command injection
  • find IDOR and object-level authorization issues
  • detect hardcoded API keys, tokens, and passwords
  • check file path handling for path traversal
  • identify race conditions and TOCTOU in concurrent code

Example prompts for the agent

  • Review this pull request for vulnerabilities — trace inputs to SQL and shell commands, check authorization
  • Find access control issues in api/users.py — especially IDOR and tenant ID filtering
  • Audit cryptography in auth/ — check algorithms, modes, and randomness sources

How to install secure-code-review

1Skills CLI (Vercel)

npx skills add securityskills/skills --skill secure-code-review -a claude-code

2Manually: put the files in place

~/.claude/skills/secure-code-review/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/secure-code-review/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about secure-code-review

How to install secure-code-review in Claude Code?

Run npx skills add securityskills/skills --skill secure-code-review -a claude-code. The skill will appear in ~/.claude/skills/secure-code-review/SKILL.md.

What does the secure-code-review skill do?

It teaches the agent to find vulnerabilities systematically: traces untrusted data to SQL, commands, HTML, and file paths, checks authorization, session management, and cryptography using vulnerability-class checklists.

Which vulnerability classes does the skill check?

SQL and NoSQL injection, command injection, XSS, path traversal, unsafe deserialization, open redirects, IDOR, session management issues, hardcoded secrets, and race conditions.

Similar skills

All skills for Security →

secure-code-review by other authors comes first.

secure-code-review zebbern secure-code-review — a Claude Code skill that reviews code against the OWASP Top 10. It flags SQL injection, XSS, SSRF, broken access control and returns ready-to-use fix code for every finding. CX Codex +1 ★ 4,719repo stars vuln-scan official anthropics vuln-scan is a Claude Code skill that statically scans source code for vulnerabilities and writes findings to JSON and markdown for triage. CX Codex +1 1,200installs security-review getsentry security-review finds injections, XSS, authorization flaws, and other vulnerabilities in code. Reports only high-confidence findings. CX Codex +1 23,800installs cc-skill-security-review sickn33 cc-skill-security-review is a Claude Code skill for reviewing security practices and spotting potential vulnerabilities. It applies to work on authentication, user input, uploads, and API endpoints. CX Codex +1 2,200installs Security Code Review kousen Security Code Review walks the agent through the OWASP Top 10 during code review, pairing each risky pattern with a safer one. Handy before a release or when reading unfamiliar code. CX Codex +1 4installs secure whawkinsiv secure audits codebases for common security flaws found in AI-generated apps. Checks for leaked API keys, broken tenant isolation, and unprotected endpoints. CX Codex +1 234installs review-security Rudolf S. review-security is a Claude Code subagent that checks code and dependency changes for vulnerabilities and supply-chain risks. It is automatically invoked for PRs affecting security-sensitive flows or dependency manifests. CX Codex ★ 587repo stars

From the same set21

The whole set →
stride-threat-modeling Run a structured STRIDE threat modeling workshop during system design. The skill maps trust boundaries, catalogs attack vectors per component, and generates backlog tickets. CX Codex +1 4,300installs jwt-security-review jwt-security-review audits JWT implementations for key confusion, weak secrets, and token lifecycle flaws. Handy when checking API authorization code. CX Codex +1 2,400installs agentic-sdlc-controls agentic-sdlc-controls audits development pipelines where AI agents commit, run tests, or deploy code. It maps credentials and defines hard boundaries for irreversible actions. CX Codex +1 1,400installs network-segmentation-review network-segmentation-review inspects traffic boundaries across local networks, firewalls, and cloud environments. It helps engineers spot routing leaks and test zone isolation. CX Codex +1 959installs owasp-top10-analysis owasp-top10-analysis guides AI through systematic web application security reviews using the OWASP Top 10 framework. Useful for pre-release security gates and vulnerability triage. CX Codex +1 813installs pci-dss-scoping Walks an agent through PCI DSS scoping: cardholder data flows, segmentation checks and a v4.0 requirements matrix. Built for audit prep. CX Codex +1 668installs ai-change-evidence ai-change-evidence builds an auditor-ready record for changes written by coding agents: who asked, what was requested, who approved. Useful when that code sits under SOC 2, ISO 27001 or PCI DSS. CX Codex +1 584installs attack-surface-recon attack-surface-recon discovers external company assets, open database ports, leaked repository tokens, and takeover risks. Best for starting security reviews or running perimeter audits. CX Codex +1 575installs

Project sponsors

Companies that keep this analytics open