security-review

security-review is a command for Claude Code from coldtatooine/vuln-skill-pack. It costs 0 tokens per session (574 once invoked), scanned A, original, MIT.

A command that reviews an application for security vulnerabilities, optionally limited to a specified path or module. It focuses on issues such as unauthorized access, injection, exposed secrets, unsafe file handling, and risky AI tool use.

In plain words
What is it for?
Use it to perform an authorized security review of a whole project or selected code, validate likely vulnerabilities, document what was checked, and identify safe fixes.
Why use it?
It helps find realistic attack paths and trace untrusted input to sensitive operations, while avoiding unsupported or speculative findings.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the vun-skill-pack plugin — 5 skills, 11 commands, 1 agent, 1 hook shipped together

Good fit Use it to perform an authorized security review of a whole project or selected code, validate likely vulnerabilities, document what was checked, and identify safe fixes.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/coldtatooine/vuln-skill-pack/security-review
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.

Clone the repo
git clone --depth 1 https://github.com/coldtatooine/vuln-skill-pack

Made for: Claude Code.

Or install vun-skill-pack, the plugin that ships this one along with the rest of its 5 skills, 11 commands, 1 agent, 1 hook.

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-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/coldtatooine/vuln-skill-pack/security-review/github.svg)](https://agentmods.dev/commands/coldtatooine/vuln-skill-pack/security-review)
Your own site
<a href="https://agentmods.dev/commands/coldtatooine/vuln-skill-pack/security-review"><img src="https://agentmods.dev/badge/commands/coldtatooine/vuln-skill-pack/security-review/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.

agentmods 80×15 button for security-review

Your own site · 80×15
<a href="https://agentmods.dev/commands/coldtatooine/vuln-skill-pack/security-review"><img src="https://agentmods.dev/badge/commands/coldtatooine/vuln-skill-pack/security-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 574 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 $0.00000 $0.00574
Opus 5 $0.00000 $0.00287
Sonnet 5 $0.00000 $0.00115
Haiku 4.5 $0.00000 $0.00057

Measured 9d ago against content hash d8b27ab3c420, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

security-review 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 9d 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.

cursor/commands/security-review.md · 30 lines

How it starts

The opening of the file, as written. The whole thing — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/security-review — Senior AppSec Review

Input: optional scope (path/module) typed after the command; default to the whole project.

Operate as a senior application security research agent doing an authorized defensive review. Optimize for true positives, precise root-cause analysis, minimal safe reproduction, and concrete fixes. Follow the operating rules in .cursor/rules/operating-rules.mdc.

Mission

Identify realistically exploitable vulnerabilities. Prioritize: auth bypass, broken access control, injection, SSRF, path traversal, deserialization, template injection, command execution, file read/write abuse, secret exposure, crypto misuse, multi-tenant isolation, unsafe agent/tool invocation, prompt injection in AI flows, business logic flaws. Avoid hallucinated findings.

Working style

Think like a red teamer doing code-assisted review. Prefer data-flow reasoning over keyword matching. Trace untrusted input to sensitive sinks. Look for trust-boundary breaks, framework footguns, and chains of "minor" issues that combine into critical. Iterate: inventory → prioritize → trace → validate → explain → patch. Keep a worklog of what you checked and ruled out.

Workflow

  1. Attack surface map — entrypoints (routes, handlers, RPC, CLI, jobs, webhooks, uploads, templating, agent/tool/MCP adapters, OAuth callbacks, admin/debug); trust boundaries; sensitive sinks (exec, SQL/NoSQL, file I/O, HTTP fetch, template render, eval, auth decisions, token issuance, redirects, serialization, secret access).
  2. Prioritize by exploitability and impact — untrusted input reaching sinks, authz gaps, reachable code first.
  3. Root-cause each lead — exact file/function/lines, source → validation gap → sink, required attacker control, realistic impact.
  4. Validate safely — static confirmation first; minimal non-destructive reproduction; benign narrowly-scoped payloads only; state what's missing if unproven.
  5. Remediate — shortest credible structural fix + a regression test idea.

Read the full file on GitHub · 30 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. 9d ago First seen · 30 lines · 0 tokens per session scan A d8b27ab3c420

Subscribe to this mod's changes

security-review is a command published in the GitHub repository coldtatooine/vuln-skill-pack (2 stars, last pushed 14d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 574 tokens. 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.