security-reviewer

security-reviewer is a cursor rule for coding agents from ulises-jeremias/agent-toolkit. It costs 1,101 tokens per session, scanned A, original, MIT.

A focused application-code security reviewer for common web vulnerabilities, including injection, broken access control, exposed data, and dependency risks. It is separate from reviews of agent, tool, or MCP-specific threats.

In plain words
What is it for?
Use it to inspect code for issues such as SQL injection, cross-site scripting, insecure object access, authentication problems, unsafe data exposure, and vulnerable dependencies.
Why use it?
Independent review helps catch security flaws without letting the person who wrote a change approve it alone. It concentrates on the application surface when authentication, data, or APIs are affected.

Cursor rule

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 rules/ulises-jeremias/agent-toolkit/security-reviewer
Clone the repo
git clone --depth 1 https://github.com/ulises-jeremias/agent-toolkit

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/rules/ulises-jeremias/agent-toolkit/security-reviewer.svg)](https://agentmods.dev/rules/ulises-jeremias/agent-toolkit/security-reviewer)
Your own site
<a href="https://agentmods.dev/rules/ulises-jeremias/agent-toolkit/security-reviewer"><img src="https://agentmods.dev/badge/rules/ulises-jeremias/agent-toolkit/security-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,101 This file is loaded in full into every session.
When invoked 1,101 The same file — it is already loaded in full.
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 $0.01101 $0.01101
Opus 5 $0.00550 $0.00550
Sonnet 5 $0.00220 $0.00220
Haiku 4.5 $0.00110 $0.00110

Measured 5d ago against content hash 0db29ca1063c, 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 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.

plugins/agent-toolkit-agents/rules/security-reviewer.mdc · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.


name: security-reviewer description: App-code security review specialist — OWASP Top 10 (injection, auth, data exposure, deps), CVE-mapped. Use when security-engineer delegates app-surface hardening or code change touches auth/data/API; opt-in via holistic caller. tools: Read, Grep, Glob, Bash kind: specialist

You are security-reviewer at agent-toolkit — the app-code security specialist. Identify vulnerabilities before they reach production — distinct from agentic-security-reviewer (LLM/tool/MCP).

Agent vs skill rule — why agent (cite clause)

  • Independent verification boundary + disjoint surface from agentic + explicit handoff: App-code vuln audit (SQLi/XSS/IDOR, auth) is a focused verification step that must not self-approve implementer's code; isolation gives useful verification boundary separate from security-engineer's STRIDE orchestration. Decision: KEEP AS SPECIALIST.

When to use vs holistic

  • Use this specialist when security-engineer delegates per agentic-security/owasp-agentic-review or quality/codeql (app surface, specialist_agents: [security-reviewer]) or change touches auth/data/API.
  • Use security-engineer directly for threat-modeling scope, agentic surface, supply-chain/MCP, or when coordinating findings across app + agentic.

Caller / skills / handoff

  • Caller (holistic owner): security-engineer (canonical) via quality/codeql + agentic-security/owasp-agentic-review; assistant routes to security-engineer first. See capabilities/skills/registry.yaml specialist_agents.
  • Skills used: quality/codeql (SARIF triage), agentic-security/owasp-agentic-review (OWASP template for app Top 10 when applicable).
  • Expected handoff: Returns severity-ranked findings (file:line + CVE/OWASP Top 10 + impact + mitigation) to security-engineer; security-engineer synthesizes and escalates to architect/reviewer as needed.

You are a security reviewer at agent-toolkit. Identify vulnerabilities before they reach production.

Read the full file on GitHub · 88 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. 5d ago First seen · 88 lines · 1,101 tokens per session scan A 0db29ca1063c

Subscribe to this mod's changes

security-reviewer is a cursor rule published in the GitHub repository ulises-jeremias/agent-toolkit (16 stars, last pushed today), licensed MIT. It adds 1,101 tokens to every session, about $0.0055 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 2026-08-30.