security-review

security-review is a skill for Claude Code, Codex from romiluz13/auto-pi. It costs 65 tokens per session (2,014 once invoked), scanned B, original, MIT.

A security review process for code changes that looks for common vulnerabilities and unsafe operations. It is one review angle alongside checking coding standards and matching the specification.

In plain words
What is it for?
Use it during code review to inspect changes for command or SQL injection, authentication mistakes, secrets, unsafe deserialization, server-side request forgery, path traversal, dangerous operations, and dependency confusion.
Why use it?
A change can meet its requirements and still introduce a security problem. Reviewing the diff separately helps spot risks such as injection, exposed secrets, unsafe file paths, or untrusted network requests.

Skill for Claude CodeCodex

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/romiluz13/auto-pi/security-review
Any agent
npx skills add romiluz13/auto-pi --skill security-review
Clone the repo
git clone --depth 1 https://github.com/romiluz13/auto-pi

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-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/romiluz13/auto-pi/security-review.svg)](https://agentmods.dev/skills/romiluz13/auto-pi/security-review)
Your own site
<a href="https://agentmods.dev/skills/romiluz13/auto-pi/security-review"><img src="https://agentmods.dev/badge/skills/romiluz13/auto-pi/security-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,014 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 $0.00065 $0.02014
Opus 5 $0.00032 $0.01007
Sonnet 5 $0.00013 $0.00403
Haiku 4.5 $0.00006 $0.00201

Measured 4d ago against content hash 835db451af60, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

security-review scanned grade B with 2 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 4d 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.

Cloud metadata endpointmediumServer-side request forgery

One request to 169.254.169.254 can return temporary IAM credentials.

- Server-side fetch/HTTP to a user-supplied URL (webhooks, image fetching, URL previews). → validate and restrict: allowlist domains, block internal IPs (127.0.0.1, 169.254.169.254, 10.x, 192.168.x), follow-redirect limi

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- **Command injection** — user input in `exec()`, `execSync()`, `spawn()` shell mode, backticks, `subprocess.run(shell=True)`. → use argument arrays (`execFile`, `spawn` without `shell: true`); never interpolate.
skills/security-review/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Review

The third review axis in auto-pi's review phase — alongside Standards (does the code follow the repo's conventions?) and Spec (does the code match what was asked for?). This axis answers: does the diff introduce security vulnerabilities?

Runs as a parallel sub-agent with fresh context — only the diff, not the builder's reasoning — so the security review is not anchored by the implementer's assumptions.

Smell catalog

Each smell reads what it ishow to spot it in the diffhow to fix. Match against the diff hunks:

  1. Injection — user-controlled input reaches a dangerous sink without sanitization.

    • SQL injection — string-concatenated queries, unparameterized query(), ORM raw queries with user input. → parameterize; use prepared statements / parameterized query builders.
    • Command injection — user input in exec(), execSync(), spawn() shell mode, backticks, subprocess.run(shell=True). → use argument arrays (execFile, spawn without shell: true); never interpolate.
    • Template injection — user input in template engines (eval, ejs, jinja2, nunjucks) that execute code. → use logic-less templates or auto-escaping; never eval user content.
    • XSS — unescaped user input rendered in HTML (innerHTML, dangerouslySetInnerHTML, |safe in Django, {!! !!} in Blade). → escape on output; use framework auto-escaping; CSP headers.
  2. Authentication / authorization — missing or bypassable access control.

    • Missing auth checks — a route, endpoint, or function that should require authentication but doesn't. → add the auth middleware/guard.
    • Privilege escalation — a user can perform actions above their role (horizontal or vertical). → check role/permission at the action site, not just the route.
    • IDOR (Insecure Direct Object Reference) — user can access another user's resource by changing an ID in the URL/params. → verify ownership: where("user_id = ?", currentUser.id).
    • Missing ownership checks — the code loads a resource by ID without checking the requester owns it. → add ownership scoping.

Read the full file on GitHub · 101 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. 4d ago First seen · 101 lines · 65 tokens per session scan B 835db451af60

Subscribe to this mod's changes

security-review is a skill published in the GitHub repository romiluz13/auto-pi (10 stars, last pushed 19d ago), licensed MIT. It adds 65 tokens to every session and 2,014 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (cloud metadata endpoint, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.