security-audit

security-audit is a skill for Claude Code, Codex from varutasu/agent-pipeline. It costs 117 tokens per session (1,430 once invoked), scanned A, original, MIT.

A security review guide for application code that lists weaknesses by severity and groups them into areas such as access control, injection, exposed secrets, and unsafe requests.

In plain words
What is it for?
Use it to audit code changes or application surfaces and produce prioritised findings with suggested fixes and file-and-line references.
Why use it?
It gives developers a structured way to find vulnerabilities before code is merged.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

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 skills/varutasu/agent-pipeline/security-audit
Any agent
npx skills add varutasu/agent-pipeline --skill security-audit
Clone the repo
git clone --depth 1 https://github.com/varutasu/agent-pipeline

Made for: Claude Code, Codex.

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/skills/varutasu/agent-pipeline/security-audit.svg)](https://agentmods.dev/skills/varutasu/agent-pipeline/security-audit)
Your own site
<a href="https://agentmods.dev/skills/varutasu/agent-pipeline/security-audit"><img src="https://agentmods.dev/badge/skills/varutasu/agent-pipeline/security-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,430 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 5.1 $0.00117 $0.01430
Opus 5 $0.00059 $0.00715
Sonnet 5 $0.00023 $0.00286
Haiku 4.5 $0.00012 $0.00143

Measured 6d ago against content hash 8148f9ea9e66, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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.

skills/security-audit/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security audit

Six-layer audit framework for application code (not infra/IAM — those are separate convoys). Outputs a severity 0–4 findings list, an executive summary, and fix suggestions with file:line citations. Deep reference: references/owasp-checklist.md.

When to invoke

  • Automatic: by role-security-auditor on every PR draft except when skip: security is set.
  • Manual: when the user says "security review", "audit this for vulnerabilities", or before merging auth/API/schema convoys.
  • Pre-merge: audit fan-out — /multitask role-reviewer + role-security-auditor + role-design-system-auditor + role-a11y-auditor.

Severity scale

Severity Meaning Treatment
4 — Critical Exploitable without unusual conditions: auth bypass, secret in client bundle, SQL/command injection on user input, IDOR on another user's data. Block merge.
3 — High Serious weakness requiring attacker effort or specific config: missing rate limit on auth, weak session TTL, missing auth on non-public route, mass assignment. Fix before merge unless documented exception in convoy.
2 — Medium Defense-in-depth gap: verbose error leaks stack trace, missing security headers, log line includes PII. Fix or track; recommend before next release.
1 — Low Hardening opportunity: inconsistent auth helper usage, missing Zod on low-risk query param. Inline in report.
0 — Info Note for maintainer; not a defect. Inline only.

The 6 layers

Run in order. Stop early only if the diff is literally comment-only.

Layer 1 — Authentication boundary

Every protected route and server action must identify the caller before doing work.

  • New or changed API routes / server actions: is there an auth gate (requireAuth, auth(), session check, Bearer verify)?
  • Auth endpoints: rate limiting present? (checkAuthRateLimit or equivalent)
  • No synthetic-admin / dev-bypass fallbacks in production paths
  • JWT/session: secret from env (fail-loud if unset), reasonable TTL, not in client bundle
  • Password handling: hashed (bcrypt/argon2), never logged, never returned in API responses

Read the full file on GitHub · 109 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 109 lines · 117 tokens per session scan A 8148f9ea9e66

Subscribe to this mod's changes

security-audit is a skill published in the GitHub repository varutasu/agent-pipeline (2 stars, last pushed 27d ago), licensed MIT. It adds 117 tokens to every session and 1,430 once invoked, about $0.0006 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.