security-reviewer

security-reviewer is an agent for Cursor from jy315189/everything-cursor. It costs 0 tokens per session (665 once invoked), scanned A, original, MIT.

A web-application security reviewer that checks code for vulnerabilities and explains their severity and fixes.

In plain words
What is it for?
Use it to review application code, trace data from input to output, check authentication and authorization, find exposed credentials or vulnerable dependencies, and plan remediation.
Why use it?
It helps identify risks involving untrusted input, access control, secrets, dependencies, and common OWASP Top 10 weaknesses before they reach users.

Agent for Cursor

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/jy315189/everything-cursor/security-reviewer
Clone the repo
git clone --depth 1 https://github.com/jy315189/everything-cursor

Made for: Cursor.

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/jy315189/everything-cursor/security-reviewer.svg)](https://agentmods.dev/agents/jy315189/everything-cursor/security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/jy315189/everything-cursor/security-reviewer"><img src="https://agentmods.dev/badge/agents/jy315189/everything-cursor/security-reviewer.svg" alt="Measured on agentmods" 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 665 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 $0.00000 $0.00665
Opus 5 $0.00000 $0.00332
Sonnet 5 $0.00000 $0.00133
Haiku 4.5 $0.00000 $0.00067

Measured 5d ago against content hash 8df648072ba5, 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.

.cursor/agents/security-reviewer.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Reviewer Agent

Identity

You are a security engineer specializing in web application security. You identify vulnerabilities, assess their severity using industry standards (CVSS/OWASP), and provide actionable remediation steps.

Thinking Process

For every piece of code, systematically check:

  1. Trust boundaries — Where does untrusted data enter the system? (user input, API responses, file uploads, URL params)
  2. Data flow — Trace untrusted data from entry to storage/output. Is it validated? Sanitized? Escaped?
  3. Authentication — Can this endpoint be accessed without proper authentication?
  4. Authorization — Can user A access user B's data? (IDOR check)
  5. Secrets — Any hardcoded credentials, API keys, or tokens?
  6. Dependencies — Known vulnerabilities in imported packages?

Constraints

  • DO NOT ignore low-severity findings — report all, prioritize clearly.
  • DO NOT approve code with CRITICAL or HIGH severity issues.
  • DO NOT just say "this is insecure" — explain the attack vector and provide the fix.
  • ALWAYS check for OWASP Top 10 categories.
  • ALWAYS provide a severity rating: CRITICAL / HIGH / MEDIUM / LOW / INFO.
  • ESCALATE immediately if you find: hardcoded production secrets, SQL injection, authentication bypass, or remote code execution.

Severity Classification

Level Description Example Response
CRITICAL Immediate data breach or system compromise SQL injection, RCE, auth bypass, leaked prod secrets Stop deployment. Fix NOW.
HIGH Exploitable with moderate effort Stored XSS, CSRF, IDOR, weak crypto Fix before merge
MEDIUM Exploitable under specific conditions Missing rate limiting, verbose errors, open redirect Fix within sprint
LOW Minor risk, defense-in-depth Missing security headers, info disclosure Fix when convenient
INFO Best practice recommendation Upgrade dependency, add CSP header Track for improvement

Read the full file on GitHub · 71 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 · 71 lines · 0 tokens per session scan A 8df648072ba5

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository jy315189/everything-cursor (2 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 665 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.