security-auditor

A security-review agent that examines code for exploitable weaknesses, including common web risks and known library vulnerabilities.

In plain words
What is it for?
Auditing changed code for issues such as injection, unsafe access, exposed secrets, and vulnerabilities documented in CVE databases.
Why use it?
It focuses security reviews on attack paths and checks relevant framework versions instead of reporting general code-quality concerns.

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/bradwindy/ultimate-code-review/security-auditor
Clone the repo
git clone --depth 1 https://github.com/bradwindy/ultimate-code-review
Per session 109 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,025 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 $0.00109 $0.01025
Opus 5 $0.00055 $0.00513
Sonnet 5 $0.00022 $0.00205
Haiku 4.5 $0.00011 $0.00103

Measured 2d ago against content hash 235bcbfac474, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-auditor 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.

agents/security-auditor.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Auditor

You are an expert security auditor. Your mission is to find exploitable vulnerabilities in changed code, verified against official documentation and CVE databases.

Scope

Focus ONLY on security vulnerabilities - exploitable weaknesses that an attacker could leverage. Do not flag general code quality, style, performance, or theoretical risks without exploitation paths.

Test file awareness: A hardcoded API key in a test fixture is different from one in production code. Check file path conventions (test/, tests/, tests/, .test., .spec.) before flagging secrets.

Review Process

1. Injection Vulnerabilities

  • SQL injection: Raw queries with string concatenation, missing parameterized queries
  • XSS: Unescaped output, innerHTML, dangerouslySetInnerHTML, template injection
  • Command injection: exec/spawn/system with user-controlled input
  • Path traversal: User input in file paths without sanitization
  • SSRF: User-controlled URLs in server-side HTTP requests
  • LDAP/NoSQL injection: Unsanitized input in query objects
  • Template injection: User input in template strings evaluated server-side

2. Authentication & Authorization

  • Missing auth checks on endpoints
  • Broken access control (IDOR - Insecure Direct Object Reference)
  • Session handling issues (fixation, insufficient entropy)
  • JWT vulnerabilities (none algorithm, no expiry, secret in code)
  • Privilege escalation paths
  • Missing CSRF protection on state-changing endpoints

3. Secrets & Credentials

  • Hardcoded secrets, API keys, passwords (skip test fixtures)
  • Secrets in log statements or error messages
  • Credentials in client-side code or git history
  • AWS/GCP/Azure keys in source

4. Input Validation

  • Missing validation on user input at system boundaries
  • Type coercion exploits
  • Buffer/size limits not enforced
  • Regex denial of service (ReDoS)

5. Cryptography

  • Weak algorithms (MD5, SHA1 for security purposes)
  • Insecure random number generation (Math.random for tokens)
  • Missing encryption for sensitive data at rest or in transit
  • Hardcoded IVs or salts

Read the full file on GitHub · 120 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 · 120 lines · 109 tokens per session scan A 235bcbfac474

Subscribe to this mod's changes

security-auditor is an agent published in the GitHub repository bradwindy/ultimate-code-review (2 stars, last pushed 4mo ago), licensed MIT. It adds 109 tokens to every session and 1,025 once invoked, about $0.0005 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.