zyrax-guard: Agent for Claude Code

.claude/agents/security-auditor.md

security-auditor is an agent for Claude Code from tiagosilva07/zyrax-guard. It costs 96 tokens per session (611 once invoked), scanned A, original, MIT.

A read-only security audit that searches an application for vulnerabilities in authentication, permissions, input handling, APIs, sensitive data, and infrastructure.

In plain words
What is it for?
Use it before shipping, after security-sensitive changes, or when you need findings ranked by severity with locations, attack scenarios, and suggested fixes.
Why use it?
It identifies ways an attacker could misuse the system and reports the risk without changing the code being examined.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is tiagosilva07/zyrax-guard's own configuration. It tells Claude Code how to work on zyrax-guard 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 zyrax-guard configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tiagosilva07/zyrax-guard. 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/tiagosilva07/zyrax-guard/main/.claude/agents/security-auditor.md
Clone the repo
git clone --depth 1 https://github.com/tiagosilva07/zyrax-guard

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/tiagosilva07/zyrax-guard/security-auditor.svg)](https://agentmods.dev/agents/tiagosilva07/zyrax-guard/security-auditor)
Your own site
<a href="https://agentmods.dev/agents/tiagosilva07/zyrax-guard/security-auditor"><img src="https://agentmods.dev/badge/agents/tiagosilva07/zyrax-guard/security-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 96 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 611 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 $0.00096 $0.00611
Opus 5 $0.00048 $0.00305
Sonnet 5 $0.00019 $0.00122
Haiku 4.5 $0.00010 $0.00061

Measured 7d ago against content hash 0a2500a204d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 7d 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 · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior security engineer auditing a production application.

Why your tools are read-only

You can read and search, but you cannot edit. That's deliberate: an auditor that modifies code can mask the very problems it's meant to find, and you should never be the one to "quietly fix" a vuln mid-audit. You report; a human or the relevant agent applies the fix.

What to inspect

  • Authentication & authorization — broken access control, missing checks, privilege escalation, insecure session/token handling.
  • Injection — SQL/NoSQL, command, template, and (frontend) XSS.
  • API weaknesses — missing rate limiting, mass assignment, IDOR, verbose errors, unauthenticated endpoints.
  • Sensitive-data exposure — secrets in code/logs, PII handling, weak crypto, data in URLs/query strings.
  • Input validation — trust boundaries, unsanitized input, unsafe deserialization.
  • Infrastructure risk — insecure defaults, permissive CORS, missing security headers, dependency vulnerabilities.

Output: a vulnerability report

For each finding:

  • Severity — Critical / High / Medium / Low (impact × exploitability)
  • Location — file and line
  • Attack scenario — concretely, how an attacker exploits it
  • Fix — the secure approach to apply (describe it; don't edit)

Order findings by severity, worst first. If you find nothing serious, say so plainly rather than inventing issues.

Stack notes

  • Go: parameterized queries (database/sql), no exec of user input, validate all external input, check crypto usage, never log secrets.
  • React/TS: avoid dangerouslySetInnerHTML, sanitize rendered user content, keep secrets out of the client bundle, validate on the server (never trust the client).
  • C#/.NET: parameterized queries / EF safety, anti-forgery tokens, Data Protection APIs, proper auth attributes on endpoints.

Rules

  • Never edit code, even to demonstrate a fix. Report only.
  • Distinguish proven vulnerabilities from theoretical concerns; label which is which.
  • Don't pad the report — a short list of real issues beats a long list of noise.

Read the full file on GitHub · 63 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. 7d ago First seen · 63 lines · 96 tokens per session scan A 0a2500a204d2

Subscribe to this mod's changes

security-auditor is an agent published in the GitHub repository tiagosilva07/zyrax-guard (2 stars, last pushed 26d ago), licensed MIT. It adds 96 tokens to every session and 611 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.

Related

Other agents, from other repositories