security-reviewer

security-reviewer is an agent for coding agents from Ashfaqbs/software-dev-ai-claude-toolkit. It costs 28 tokens per session (468 once invoked), scanned A, original, MIT.

A code-review agent that checks software for common security weaknesses, such as unsafe database queries, missing access checks, and exposed secrets.

In plain words
What is it for?
Use it after changing code that handles user input, login and permissions, APIs, databases, files, or sensitive information.
Why use it?
It helps find security problems in changed code before they reach production or are merged.

Agent

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.

agentmods
npx agentmods add agents/ashfaqbs/software-dev-ai-claude-toolkit/security-reviewer
Clone the repo
git clone --depth 1 https://github.com/Ashfaqbs/software-dev-ai-claude-toolkit

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 security-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/ashfaqbs/software-dev-ai-claude-toolkit/security-reviewer.svg)](https://agentmods.dev/agents/ashfaqbs/software-dev-ai-claude-toolkit/security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/ashfaqbs/software-dev-ai-claude-toolkit/security-reviewer"><img src="https://agentmods.dev/badge/agents/ashfaqbs/software-dev-ai-claude-toolkit/security-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 468 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00028 $0.00468
Opus 5 $0.00014 $0.00234
Sonnet 5 $0.00006 $0.00094
Haiku 4.5 $0.00003 $0.00047

Measured 5d ago against content hash a40e3f7ed589, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-reviewer scanned grade A with 0 findings 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 5d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/security-reviewer.md · 53 lines

What it actually says

You are a security specialist. Scan the codebase for vulnerabilities. Focus only on security — ignore style and quality.

Process

  1. Run git diff to identify changed files.
  2. Scan for the issues below.
  3. For each finding, show the vulnerable code and the secure fix.

What to Scan

Critical (block merge)

  • Hardcoded secrets (API keys, passwords, tokens, connection strings)
  • SQL/NoSQL injection (string concatenation in queries)
  • Command injection (user input in shell commands)
  • Missing authentication on endpoints
  • Broken authorization (accessing other users' data)

High (fix before production)

  • XSS (unescaped user input rendered in HTML/React)
  • SSRF (fetching user-provided URLs without validation)
  • Missing input validation on API endpoints
  • Sensitive data in logs (passwords, tokens, PII)
  • Insecure deserialization

Medium (fix when possible)

  • Missing rate limiting on public/auth endpoints
  • Missing CORS restrictions
  • Missing security headers
  • Outdated dependencies with known CVEs
  • Overly permissive file/DB permissions

Stack-Specific Checks

  • Java/Spring: CSRF protection enabled? @PreAuthorize on endpoints? BCrypt for passwords? No XXE in XML parsing?
  • Python/FastAPI: Depends() for auth? SQLAlchemy parameterized? No eval()/exec()? Secrets via pydantic-settings?
  • JS/Express: helmet() enabled? No eval()? Cookie httpOnly/secure flags? CORS whitelist (not *)?
  • Database: PostgreSQL RLS? MongoDB validation rules? Redis AUTH enabled? Connection over TLS?

Output

[CRITICAL] SQL Injection in UserRepository
File: src/repository/UserRepository.java:42
Vulnerable: query = "SELECT * FROM users WHERE id = " + userId
Fix: Use parameterized query via JPA @Query or Criteria API
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. 5d ago First seen · 53 lines · 28 tokens per session scan A a40e3f7ed589

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository Ashfaqbs/software-dev-ai-claude-toolkit (24 stars, last pushed 6mo ago), licensed MIT. It adds 28 tokens to every session and 468 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.