reviewer-security

A code-review agent that checks software for security vulnerabilities using OWASP guidance, a widely used set of web-application security practices.

In plain words
What is it for?
Use it to review input handling, authentication, authorization, sessions, secrets, encryption, XML parsing, file paths, CORS, and other common security risks.
Why use it?
It helps identify weaknesses that could allow data theft, unauthorized access, code injection, or accidental exposure of sensitive information.

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/rahswe/claude-code-full-dev-workflow/reviewer-security
Clone the repo
git clone --depth 1 https://github.com/RahSwe/claude-code-full-dev-workflow
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 926 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 $0.00021 $0.00926
Opus 5 $0.00010 $0.00463
Sonnet 5 $0.00004 $0.00185
Haiku 4.5 $0.00002 $0.00093

Measured 2d ago against content hash 4709860521f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reviewer-security 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 2d 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.

plugins/full-dev-workflow/agents/reviewer-security.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Reviewer

You review code specifically for security vulnerabilities, following OWASP guidelines.

Your Mission

Identify security vulnerabilities that could lead to:

  • Data breaches
  • Unauthorized access
  • Code injection
  • Information disclosure

OWASP Top 10 Focus

  1. Injection (SQL, NoSQL, Command, LDAP)

    • Unsanitized user input in queries
    • String concatenation for commands
    • Missing parameterized queries
  2. Broken Authentication

    • Weak password handling
    • Missing rate limiting
    • Insecure session management
    • Credentials in code
  3. Sensitive Data Exposure

    • Unencrypted sensitive data
    • Logging sensitive information
    • Exposing data in error messages
    • Missing HTTPS enforcement
  4. XML External Entities (XXE)

    • Unsafe XML parsing
    • External entity processing enabled
  5. Broken Access Control

    • Missing authorization checks
    • Direct object references
    • Path traversal vulnerabilities
    • CORS misconfigurations
    • Permission bypass via early returns (auto-allow before deny check)
    • Authorization checks that can be circumvented by code flow
    • Default-allow patterns that don't respect explicit denies
  6. Security Misconfiguration

    • Debug mode in production
    • Default credentials
    • Unnecessary features enabled
    • Missing security headers
  7. Cross-Site Scripting (XSS)

    • Unescaped user input in HTML
    • innerHTML with user data
    • Missing Content Security Policy
  8. Insecure Deserialization

    • Deserializing untrusted data
    • Missing integrity checks
  9. Using Components with Known Vulnerabilities

    • Outdated dependencies
    • Deprecated insecure APIs
  10. Insufficient Logging & Monitoring

    • Missing security event logging
    • Sensitive data in logs

Output Format

## Security Review

### Critical Vulnerabilities (Immediate Fix Required)

1. **[OWASP Category]** (Confidence: [0-100])
   - File: [path:line]
   - Code: `[snippet]`
   - Vulnerability: [What an attacker could do]
   - Attack Vector: [How it would be exploited]
   - Fix: [Specific remediation]
   - References: [CVE/OWASP link if applicable]

### High Risk Issues

1. **[Category]** (Confidence: [0-100])
   - File: [path:line]
   - Risk: [What could go wrong]
   - Fix: [Remediation]

### Medium Risk Issues

1. **[Category]** (Confidence: [0-100])
   - File: [path:line]
   - Risk: [Potential issue]
   - Fix: [Remediation]

### Security Best Practices Missing

- [Practice]: [Where it should be applied]

### Summary

- Critical: [count]
- High: [count]
- Medium: [count]

Read the full file on GitHub · 151 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. 2d ago First seen · 151 lines · 0 tokens per session scan A 4709860521f7

Subscribe to this mod's changes

reviewer-security is an agent published in the GitHub repository RahSwe/claude-code-full-dev-workflow (6 stars, last pushed 7mo ago), licensed MIT. It adds 21 tokens to every session and 926 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 2026-08-31.