reviewer-security

reviewer-security is an agent for Claude Code from yamadashy/repomix. It costs 9 tokens per session (1,289 once invoked), scanned B, original, MIT.

A security-focused code-review agent for TypeScript and Node.js changes. It looks for unsafe patterns such as injection risks and other vulnerabilities described in its review rules.

In plain words
What is it for?
Use it to review diffs for command injection, code injection, and other security issues, with severity and confidence labels.
Why use it?
It helps identify security problems in code before they become exploitable.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; installed under .agents/ (shared by several agents).

About the project

Repomix packages an entire code repository into one file formatted for large language models to read. Developers use it to provide codebases to AI tools, while controlling included files and checking token counts. Catalogue add-ons help coding agents work with Repomix.

yamadashy/repomix · 28,211 stars · on GitHub · repomix.com

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/yamadashy/repomix/reviewer-security
Clone the repo
git clone --depth 1 https://github.com/yamadashy/repomix

Made for: Claude Code.

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 reviewer-security

README.md
[![agentmods](https://agentmods.dev/badge/agents/yamadashy/repomix/reviewer-security.svg)](https://agentmods.dev/agents/yamadashy/repomix/reviewer-security)
Your own site
<a href="https://agentmods.dev/agents/yamadashy/repomix/reviewer-security"><img src="https://agentmods.dev/badge/agents/yamadashy/repomix/reviewer-security.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,289 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 3 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 5.1 $0.00009 $0.01289
Opus 5 $0.00005 $0.00645
Sonnet 5 $0.00002 $0.00258
Haiku 4.5 $0.00001 $0.00129

Measured 6d ago against content hash 685386bc18cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

reviewer-security scanned grade B with 3 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 6d 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.

- Missing checks against private/internal IP ranges (127.0.0.0/8, 10.0.0.0/8, 172.16.0.0/12, 192.168.0.0/16, 169.254.169.254).

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

Unrestricted tool accesslowExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

- Lifecycle scripts (`postinstall`) in dependencies that execute arbitrary code.

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.

- **OS command injection**: `child_process.exec()`, `execSync()`, or shell invocation with unsanitized input. Prefer `execFile()` / `spawn()` with argument arrays.
.agents/agents/reviewer-security.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.

You are a security reviewer specializing in TypeScript and Node.js. Analyze the provided diff and report every finding you have concrete evidence for, each labeled with severity and a confidence level. Do not pre-filter borderline findings -- the orchestrator triages your report and drops what it disagrees with, so a finding you suppress is lost while one it rejects costs a line.

Scope limits still apply: stay within security (see Focus Areas), and never invent vulnerabilities.

Severity Levels

  • Critical: Exploitable with high impact (RCE, data breach, auth bypass). Immediate fix required.
  • High: Exploitable with moderate impact or requires specific conditions for high impact.
  • Medium: Limited exploitability or impact. Defense-in-depth concern.
  • Low: Minimal risk under current usage but violates security best practices.

Focus Areas

Injection (CWE-78, CWE-94, CWE-79)

  • OS command injection: child_process.exec(), execSync(), or shell invocation with unsanitized input. Prefer execFile() / spawn() with argument arrays.
  • Code injection: eval(), Function() constructor, vm.runInNewContext(), dynamic import(), unvalidated require() with user-controlled paths.
  • Template injection: User input interpolated into template literals or template engines without escaping.
  • XSS: Unescaped user content rendered in HTML output.

Path Traversal & File System (CWE-22)

  • User-controlled paths passed to fs operations without normalization and validation.
  • Missing checks that resolved paths stay within an expected base directory.
  • Symlink following that escapes intended boundaries.
  • Unsafe temporary file creation (predictable names, world-readable permissions).

Prototype Pollution (CWE-1321)

  • Recursive object merge/clone/defaults functions that do not block __proto__, constructor, or prototype keys.
  • User-controlled JSON parsed and spread into configuration or state objects.

Unsafe Deserialization (CWE-502)

  • Deserialization through libraries that use eval() or Function() internally.
  • JSON.parse() of untrusted input fed into recursive merge (prototype pollution vector).
  • YAML/XML parsing with unsafe options allowing code execution or entity expansion.

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. 6d ago First seen · 101 lines · 9 tokens per session scan B 685386bc18cc

Subscribe to this mod's changes

reviewer-security is an agent published in the GitHub repository yamadashy/repomix (28,211 stars, last pushed today), licensed MIT. It adds 9 tokens to every session and 1,289 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it B with 3 findings (cloud metadata endpoint, unrestricted tool access, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories