security-audit

security-audit is a skill for Claude Code from evgenii-studitskikh/Claude-Code-SaaS-Studio. It costs 59 tokens per session (479 once invoked), scanned A, original, MIT.

A security review for a SaaS codebase or set of code changes. It checks common risks such as login handling, customer-data separation, secrets, input validation, payment webhooks, security headers, and vulnerable packages.

In plain words
What is it for?
Use it to audit a code diff or an entire repository and produce a report with each finding's location and suggested fix.
Why use it?
It reveals security problems before release and ranks them by severity, so the most urgent issues can be addressed first.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; names the AskUserQuestion tool.

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/evgenii-studitskikh/claude-code-saas-studio/security-audit
Any agent
npx skills add evgenii-studitskikh/Claude-Code-SaaS-Studio --skill security-audit
Clone the repo
git clone --depth 1 https://github.com/evgenii-studitskikh/Claude-Code-SaaS-Studio

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-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/evgenii-studitskikh/claude-code-saas-studio/security-audit.svg)](https://agentmods.dev/skills/evgenii-studitskikh/claude-code-saas-studio/security-audit)
Your own site
<a href="https://agentmods.dev/skills/evgenii-studitskikh/claude-code-saas-studio/security-audit"><img src="https://agentmods.dev/badge/skills/evgenii-studitskikh/claude-code-saas-studio/security-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 479 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 $0.00059 $0.00479
Opus 5 $0.00030 $0.00239
Sonnet 5 $0.00012 $0.00096
Haiku 4.5 $0.00006 $0.00048

Measured 5d ago against content hash b6bf4be5e83a, 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 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.

.claude/skills/security-audit/SKILL.md · 22 lines

What it actually says

Find and rank security risks before launch. Non-autonomous: report findings and proposed fixes; never auto-apply fixes without sign-off.

Phases

  1. Scope — Default to diff (staged/branch changes vs the base branch). If there is no active diff (nothing staged and no changes vs the base branch), automatically fall back to full (whole repo). Confirm the chosen scope with the user before proceeding.
  2. Checklist pass — review against: auth/session checks on protected routes; Supabase RLS + tenant scoping (no client-supplied tenant id); secrets only in env (cross-check the validate-commit hook); input validation at boundaries (zod); Stripe webhook signature + idempotency; security headers (Content-Security-Policy (CSP), Strict-Transport-Security (HSTS), X-Content-Type-Options: nosniff, X-Frame-Options, Referrer-Policy); error sanitization.
  3. Dependency audit — run npm audit --omit=dev (if a project exists) and note high/critical advisories; confirm a committed lockfile.
  4. Rank findings — fill .claude/templates/security-audit.md into docs/specs/security-audit.md with each finding: title, severity (Critical/High/Medium/Low), location, and recommended fix. Honor review intensity.
  5. Verdict — summarize: PASS (no open High/Critical) or BLOCK (list the blockers). This verdict is what /launch-checklist reads.

Output

docs/specs/security-audit.md + a PASS/BLOCK verdict. Proposes fixes; applies nothing without approval.

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 · 22 lines · 59 tokens per session scan A b6bf4be5e83a

Subscribe to this mod's changes

security-audit is a skill published in the GitHub repository evgenii-studitskikh/Claude-Code-SaaS-Studio (1 stars, last pushed 2mo ago), licensed MIT. It adds 59 tokens to every session and 479 once invoked, about $0.0003 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 skills, from other repositories

autoprompt

Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.

Spielewoy/autoprompt-skill · 56 tokens

create-modal

Create declarative modals using the modal library API. Covers modal types (confirm, input, select, form), sections (Text, Buttons, Input, Textarea, Checkbox, Select, List, Combo, When, Custom), rendering with OverlayModal, and keyboard/mouse handling. Use when adding modals or dialogs to the application.

marcus/sidecar · 71 tokens

ap-juror

L4 terminal leaf - G7 SIGN-OFF. One independent sign-off panel seat that saw none of the intermediate work. Binary PASS/FAIL on opened evidence; default-FAIL. A FAIL naming a P0/P1 blocker is NOT arbitrable into PASS.

Spielewoy/autoprompt-skill · 58 tokens

openlore-brainstorm

Transform a feature idea into an annotated story using a Domain Sketch or Constrained Option Tree. Use when asked to brainstorm, explore, or shape a feature before implementation.

clay-good/OpenLore · 40 tokens

gemigo-cli

Use when the user wants to publish an already-built static website or front-end app through GemiGo, such as a Vite/React/Vue static build, plain HTML/CSS/JS page, landing page, demo, docs site, or small browser app, and get a hosted public URL.

Peiiii/nextclaw · 65 tokens

agenticx-query-data-source

Use when the user asks about verifiable quantitative facts (stock prices, financial indicators, macro data, company registry, academic metrics, legal statutes) that must come from a live data source rather than training memory.

DemonDamon/AgenticX · 49 tokens