secure-code-review

secure-code-review is a skill for Claude Code from latestaiagents/agent-skills. It costs 60 tokens per session (1,625 once invoked), scanned A, original, MIT.

A structured method for reviewing code for security weaknesses, especially in pull requests and security-sensitive parts of an application.

In plain words
What is it for?
Use it for security-focused code reviews, production checks, compliance work, or reviews after an incident.
Why use it?
It gives reviewers a consistent way to examine input handling, authentication, authorization, data protection, and trust boundaries.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

Part of the security-guardian plugin — 10 skills, 2 commands shipped together

Good fit Use it for security-focused code reviews, production checks, compliance work, or reviews after an incident.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/latestaiagents/agent-skills/secure-code-review
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add latestaiagents/agent-skills --skill secure-code-review
Clone the repo
git clone --depth 1 https://github.com/latestaiagents/agent-skills

Made for: Claude Code.

Or install security-guardian, the plugin that ships this one along with the rest of its 10 skills, 2 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for secure-code-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/latestaiagents/agent-skills/secure-code-review.svg)](https://agentmods.dev/skills/latestaiagents/agent-skills/secure-code-review)
Your own site
<a href="https://agentmods.dev/skills/latestaiagents/agent-skills/secure-code-review"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/secure-code-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,625 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00060 $0.01625
Opus 5 $0.00030 $0.00813
Sonnet 5 $0.00012 $0.00325
Haiku 4.5 $0.00006 $0.00162

Measured 4d ago against content hash 24c701a0f957, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

secure-code-review scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

fetch(url);
plugins/security-guardian/skills/common/secure-code-review/SKILL.md · 296 lines

How it starts

The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Secure Code Review

A systematic approach to finding security vulnerabilities in code.

When to Use

  • Reviewing pull requests
  • Auditing security-critical code
  • Before production deployments
  • Compliance requirements
  • After security incidents

Review Methodology

1. Understand Context

## Pre-Review Questions

- [ ] What does this code do?
- [ ] What data does it handle? (PII, financial, auth)
- [ ] Who can access this functionality?
- [ ] What are the trust boundaries?
- [ ] What could go wrong?

2. Security Review Checklist

## Input Handling
- [ ] All user input validated
- [ ] Input length limits enforced
- [ ] Type checking performed
- [ ] Whitelisting over blacklisting

## Authentication
- [ ] Authentication required where needed
- [ ] Passwords hashed properly (bcrypt/argon2)
- [ ] Session management secure
- [ ] MFA considered for sensitive actions

## Authorization
- [ ] Authorization checks on all endpoints
- [ ] Resource ownership verified
- [ ] No privilege escalation paths
- [ ] Default deny policy

## Data Protection
- [ ] Sensitive data encrypted at rest
- [ ] TLS for data in transit
- [ ] No sensitive data in logs
- [ ] Proper data masking

## Injection Prevention
- [ ] Parameterized queries used
- [ ] No eval() with user data
- [ ] Command injection prevented
- [ ] XSS prevention (encoding/CSP)

## Error Handling
- [ ] No stack traces to users
- [ ] No sensitive data in errors
- [ ] Proper logging of security events

## Dependencies
- [ ] No known vulnerabilities
- [ ] Packages from trusted sources
- [ ] Lock files up to date

3. High-Risk Areas

Focus extra attention on:

// File uploads
app.post('/upload', (req, res) => {
  // Check: file type validation, size limits, storage location
});

// Authentication
app.post('/login', (req, res) => {
  // Check: rate limiting, timing attacks, error messages
});

// Authorization
app.get('/admin/*', (req, res) => {
  // Check: role verification, access control
});

// Data queries
db.query(sql, params);
// Check: parameterized queries, access control

// External API calls
fetch(url);
// Check: SSRF prevention, URL validation

// Serialization
JSON.parse(input);
pickle.loads(input);
// Check: deserialization safety

// Crypto operations
crypto.createCipher();
// Check: algorithm strength, key management

Read the full file on GitHub · 296 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 296 lines · 60 tokens per session scan A 24c701a0f957

Subscribe to this mod's changes

secure-code-review is a skill published in the GitHub repository latestaiagents/agent-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 60 tokens to every session and 1,625 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.