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.
curl -O https://raw.githubusercontent.com/tiagosilva07/zyrax-guard/main/.claude/agents/security-auditor.mdgit clone --depth 1 https://github.com/tiagosilva07/zyrax-guardWrote 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.
[](https://agentmods.dev/agents/tiagosilva07/zyrax-guard/security-auditor)<a href="https://agentmods.dev/agents/tiagosilva07/zyrax-guard/security-auditor"><img src="https://agentmods.dev/badge/agents/tiagosilva07/zyrax-guard/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.
<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="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00096 | $0.00611 |
| Opus 5.5 | $0.00038 | $0.00244 |
| Sonnet 5.5 | $0.00019 | $0.00122 |
| Haiku 4.5 | $0.00010 | $0.00061 |
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.
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), noexecof user input, validate all external input, checkcryptousage, 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.
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.
- 1mo ago First seen · 63 lines · 96 tokens per session scan A 0a2500a204d2
security-auditor is an agent published in the GitHub repository tiagosilva07/zyrax-guard (2 stars, last pushed 2mo ago), licensed MIT. It adds 96 tokens to every session and 611 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.