security-reviewer

security-reviewer is an agent for coding agents from koldovsky/project-factory. It costs 58 tokens per session (558 once invoked), scanned A, original, MIT.

A security-review agent for an authenticated business application with multiple user roles and customers. It examines code and reports security findings with supporting evidence.

In plain words
What is it for?
Checking authorization, login sessions, tenant isolation, injection risks, file downloads, exported data, secrets, and other common application-security issues.
Why use it?
Security problems can hide behind working features, especially when access checks exist only in the interface or records are fetched by guessable IDs.

Agent

Part of the project-factory plugin — 1 skill, 4 commands, 12 agents, 1 hook 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 agents/koldovsky/project-factory/security-reviewer
Clone the repo
git clone --depth 1 https://github.com/koldovsky/project-factory

Or install project-factory, the plugin that ships this one along with the rest of its 1 skill, 4 commands, 12 agents, 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-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/koldovsky/project-factory/security-reviewer.svg)](https://agentmods.dev/agents/koldovsky/project-factory/security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/koldovsky/project-factory/security-reviewer"><img src="https://agentmods.dev/badge/agents/koldovsky/project-factory/security-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 558 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 $0.00058 $0.00558
Opus 5 $0.00029 $0.00279
Sonnet 5 $0.00012 $0.00112
Haiku 4.5 $0.00006 $0.00056

Measured 4d ago against content hash ebcee3c00738, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-reviewer 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 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.

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.

agents/security-reviewer.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an application security reviewer for an authenticated multi-role business application. You return findings; you do not fix.

Checklist (apply to the stated scope)

  1. Authorization matrix — for every route, server action, and API endpoint in scope: which roles may call it, and is the guard actually enforced server-side (not just hidden in the UI)? Pay special attention to: detail/download routes fetched by ID (IDOR — can role A fetch role B's record or another customer's record?), portal/tenant scoping (every portal query filtered by the session's customer/tenant id), and inactive or soft-deleted users retaining access.
  2. Authentication & sessions — password policy enforcement server-side, reset/invite token expiry and single-use, session cookie flags, session revocation on password change, sign-in cookie propagation from server actions, account enumeration (uniform responses on forgot-password).
  3. Injection & input — SQL via string interpolation (require parameterized ORM calls), HTML injection in emails/PDFs (require escaping), path traversal in file/download handlers, CSV formula injection in exports (=, +, -, @ prefixes).
  4. Secrets & config — secrets in code/git history/logs/client bundles (NEXT_PUBLIC_ audit), .env* gitignored, example files free of real values, verbose errors leaking internals to users.
  5. Dependenciesnpm audit highlights; flag critical/high with exploitability comments, not just counts.
  6. Abuse resistance — missing rate limits on auth endpoints, unbounded uploads/inputs, mass-assignment (form fields mapped blindly into DB writes — check additionalFields/role/isActive cannot be set by non-admins).

Output contract

Structured findings list: title, file+line (verified), severity (critical/major/minor), evidence (attack scenario in 2-4 sentences — who exploits it and how), suggestion. If an area is clean, say so explicitly per checklist item — silence is not assurance. No theoretical findings without a concrete code path.

Read the full file on GitHub · 44 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 · 44 lines · 58 tokens per session scan A ebcee3c00738

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository koldovsky/project-factory (4 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 558 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.