security-audit

security-audit is a command for coding agents from ayalaphiscan/web-security-guard. It costs 41 tokens per session (642 once invoked), scanned A, original, MIT.

A command that checks a project for security problems and produces a report with findings and suggested corrections.

In plain words
What is it for?
Use it to inspect source code, configuration, stored secrets, authentication, payment handling, security settings, and third-party packages.
Why use it?
It helps reveal issues that are easy to miss, including exposed secrets, unsafe input handling, weak sign-in protection, payment mistakes, risky settings, and vulnerable dependencies.

Command

Part of the web-security-guard plugin — 6 skills, 2 commands shipped together

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 commands/ayalaphiscan/web-security-guard/security-audit
Clone the repo
git clone --depth 1 https://github.com/ayalaphiscan/web-security-guard

Or install web-security-guard, the plugin that ships this one along with the rest of its 6 skills, 2 commands.

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-audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/ayalaphiscan/web-security-guard/security-audit.svg)](https://agentmods.dev/commands/ayalaphiscan/web-security-guard/security-audit)
Your own site
<a href="https://agentmods.dev/commands/ayalaphiscan/web-security-guard/security-audit"><img src="https://agentmods.dev/badge/commands/ayalaphiscan/web-security-guard/security-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 642 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 $0.00041 $0.00642
Opus 5 $0.00020 $0.00321
Sonnet 5 $0.00008 $0.00128
Haiku 4.5 $0.00004 $0.00064

Measured 5d ago against content hash 474695166559, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-audit 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 5d 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.

commands/security-audit.md · 25 lines

What it actually says

Esegui un audit di sicurezza del progetto nella cartella di lavoro corrente (se non c'è una cartella connessa, chiedila con request_cowork_directory). Rispondi nella lingua dell'utente.

Analizza il codice cercando, in ordine di gravità:

  1. Segreti nel codice: API key, password, token, chiavi private hardcoded o in file committati (controlla anche che .env sia in .gitignore).
  2. Injection: query SQL costruite con concatenazione, input utente in comandi shell, eval, percorsi file da input.
  3. XSS: input utente inserito in HTML senza escaping (innerHTML, template senza autoescape).
  4. Autenticazione: password non hashate o con hash deboli (MD5/SHA1), assenza di rate limiting sul login, sessioni/cookie senza flag di sicurezza, mancanza di verifica email o 2FA dove appropriato (confronta con la skill autenticazione-sicura).
  5. Pagamenti: dati carta salvati o loggati, webhook senza verifica firma, prezzi presi dal client (confronta con la skill privacy-pagamenti).
  6. Configurazione: security headers mancanti, CORS aperto, errori che espongono stack trace, HTTP senza redirect a HTTPS (confronta con la skill hardening-siti).
  7. Dipendenze: esegui npm audit o pip-audit se disponibili nel sandbox.
  8. Repo GitHub: presenza di workflow di sicurezza e dependabot (skill sicurezza-github).

Produci un report con: riepilogo (numero problemi per gravità Critica/Alta/Media/Bassa), per ogni problema il file e la riga, perché è pericoloso (in linguaggio semplice), e la correzione concreta. Salva il report come security-audit.md negli outputs e presentalo con present_files.

Alla fine chiedi all'utente se vuole che applichi subito le correzioni (in tal caso applica le skill di questo plugin).


English: run a security audit of the current working folder's project (reply in the user's language). Scan in order of severity: hardcoded secrets, injection (SQL/shell/eval/paths), XSS, authentication weaknesses, payment-data handling, configuration (headers, CORS, stack traces, HTTPS), vulnerable dependencies (npm audit/pip-audit), GitHub security workflows. Produce a report (counts by Critical/High/Medium/Low, file and line per finding, plain-language risk and concrete fix), save it as security-audit.md in outputs and present it. Finally ask the user whether to apply the fixes right away using this plugin's skills.

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. 5d ago First seen · 25 lines · 41 tokens per session scan A 474695166559

Subscribe to this mod's changes

security-audit is a command published in the GitHub repository ayalaphiscan/web-security-guard (4 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 642 once invoked, about $0.0002 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.