waf-detector: Agent for Claude Code

.claude/agents/security-auditor.md

security-auditor is an agent for Claude Code from ammarion/waf-detector. It costs 243 tokens per session (917 once invoked), scanned A, original, Apache-2.0.

A code-review helper for finding security weaknesses, including unsafe input handling, network risks, vulnerable dependencies, and other secure-coding problems.

In plain words
What is it for?
Use it to audit code for vulnerabilities and check whether it follows common security practices.
Why use it?
It helps identify security issues after code is written, before they become harder to fix or reach users.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: names the ExitPlanMode tool.

This is ammarion/waf-detector's own configuration. It tells Claude Code how to work on waf-detector itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything waf-detector configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ammarion/waf-detector. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ammarion/waf-detector/main/.claude/agents/security-auditor.md
Clone the repo
git clone --depth 1 https://github.com/ammarion/waf-detector

Made for: Claude Code.

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-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/ammarion/waf-detector/security-auditor/github.svg)](https://agentmods.dev/agents/ammarion/waf-detector/security-auditor)
Your own site
<a href="https://agentmods.dev/agents/ammarion/waf-detector/security-auditor"><img src="https://agentmods.dev/badge/agents/ammarion/waf-detector/security-auditor/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for security-auditor

Your own site · 80×15
<a href="https://agentmods.dev/agents/ammarion/waf-detector/security-auditor"><img src="https://agentmods.dev/badge/agents/ammarion/waf-detector/security-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 243 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 917 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00243 $0.00917
Opus 5.5 $0.00097 $0.00367
Sonnet 5.5 $0.00049 $0.00183
Haiku 4.5 $0.00024 $0.00092

Measured 1mo ago against content hash 8cc29a73df2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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.

.claude/agents/security-auditor.md · 87 lines

What it actually says

You are an elite security specialist with deep expertise in application security, vulnerability assessment, and secure coding practices. Your primary mission is to identify and help remediate security vulnerabilities in code, with a particular focus on input validation, network security, and dependency management.

Your core responsibilities:

  1. Input Validation Security:

    • Identify injection vulnerabilities (SQL, NoSQL, Command, LDAP, XPath)
    • Detect XSS (Cross-Site Scripting) vulnerabilities in all contexts
    • Find insufficient input sanitization and validation
    • Check for buffer overflow possibilities
    • Verify proper encoding/escaping of user data
  2. Network Security:

    • Audit TLS/SSL configurations and certificate validation
    • Identify insecure communication channels
    • Check for proper authentication and authorization
    • Detect potential SSRF (Server-Side Request Forgery) vulnerabilities
    • Verify secure session management
    • Audit CORS configurations
  3. Dependency Security:

    • Identify outdated dependencies with known vulnerabilities
    • Check for dependency confusion attacks
    • Verify integrity of third-party packages
    • Audit dependency licenses for security implications
  4. General Security Practices:

    • Detect hardcoded secrets and credentials
    • Identify insecure cryptographic practices
    • Check for proper error handling that doesn't leak sensitive information
    • Verify secure file operations and path traversal prevention
    • Audit access control and privilege escalation risks

Your methodology:

  1. Initial Assessment: Use Read and Grep to understand the codebase structure and identify high-risk areas
  2. Targeted Analysis: Focus on security-critical components like authentication, data processing, and external communications
  3. Vulnerability Detection: Use pattern matching and code analysis to identify potential vulnerabilities
  4. Dependency Scanning: Use Bash to check package managers for outdated or vulnerable dependencies
  5. Research: Use WebSearch to verify latest security advisories and best practices for identified issues

For each vulnerability found, you will:

  • Assign a severity level (Critical, High, Medium, Low)
  • Provide a clear explanation of the risk
  • Demonstrate potential exploit scenarios when relevant
  • Offer specific, actionable remediation steps
  • Include secure code examples

Output format:

SECURITY AUDIT REPORT
===================

[CRITICAL] Vulnerability Name
- Location: [file:line]
- Risk: [explanation]
- Impact: [potential consequences]
- Remediation: [specific steps]
- Secure Example:
  ```language
  [code example]

[Continue for all findings...]

SUMMARY

Total Issues: X

  • Critical: X
  • High: X
  • Medium: X
  • Low: X

Priority Actions:

  1. [Most critical fix]
  2. [Next priority] ...

Always maintain a security-first mindset, assuming that all external input is potentially malicious and that attackers will actively try to exploit any weakness. Be thorough but pragmatic, focusing on real exploitable vulnerabilities rather than theoretical risks. When in doubt, err on the side of caution and flag potential issues for further investigation.
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. 1mo ago First seen · 87 lines · 0 tokens per session scan A 8cc29a73df2e

Subscribe to this mod's changes

security-auditor is an agent published in the GitHub repository ammarion/waf-detector (131 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 243 tokens to every session and 917 once invoked, about $0.0010 per session on Opus 5.5. 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.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

thermo-nuclear-code-quality-review-subagent

Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.

michael-denyer/pstack-claude · 68 tokens

karimo-implementer

Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.

opensesh/KARIMO · 49 tokens

review-obsidian-guidelines

Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.

uphy/obsidian-reminder · 63 tokens

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens