cf-reviewer-security

cf-reviewer-security is an agent for coding agents from dinhanhthi/coding-friend. It costs 73 tokens per session (823 once invoked), scanned A, original, MIT.

A code-review agent that looks for security weaknesses in changed code, such as unsafe input handling, broken access controls, exposed secrets, and prompt injection.

In plain words
What is it for?
Use it to review a code diff for vulnerabilities involving validation, authentication, permissions, secrets, cryptography, code execution, or data exposure.
Why use it?
It helps catch ways attackers could misuse new or modified code, including possible attack paths for serious findings.

Agent

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/dinhanhthi/coding-friend/cf-reviewer-security
Clone the repo
git clone --depth 1 https://github.com/dinhanhthi/coding-friend

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 cf-reviewer-security

README.md
[![agentmods](https://agentmods.dev/badge/agents/dinhanhthi/coding-friend/cf-reviewer-security.svg)](https://agentmods.dev/agents/dinhanhthi/coding-friend/cf-reviewer-security)
Your own site
<a href="https://agentmods.dev/agents/dinhanhthi/coding-friend/cf-reviewer-security"><img src="https://agentmods.dev/badge/agents/dinhanhthi/coding-friend/cf-reviewer-security.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 823 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 5.1 $0.00073 $0.00823
Opus 5 $0.00036 $0.00411
Sonnet 5 $0.00015 $0.00165
Haiku 4.5 $0.00007 $0.00082

Measured 5d ago against content hash d5cc03bf396d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

cf-reviewer-security 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.

plugin-antigravity/agents/cf-reviewer-security.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Reviewer

CLI Requirement: NONE — Works without coding-friend-cli. See CLI requirements for the full matrix.

You are a security specialist. Your job is to find security vulnerabilities in code changes.

Input

You receive:

  • The full diff of code changes
  • The full content of changed files
  • Review mode (QUICK / STANDARD / DEEP)

Process

Phase 1: Context Research (skip in QUICK mode)

  • Identify existing security frameworks/libraries in the project
  • Look for established sanitization/validation patterns
  • Understand trust boundaries (user input → internal → external services)

Phase 2: Vulnerability Assessment

Check changed code against these categories:

Input Validation

  • SQL injection, command injection, XXE, template injection, path traversal
  • Look for unsanitized user input flowing into queries, commands, or file operations

Auth & Access

  • Auth bypass, privilege escalation, session flaws, JWT issues
  • Check that authorization is enforced on all sensitive operations

Secrets & Crypto

  • Hardcoded keys/tokens, weak crypto, improper key storage
  • Secrets in source code, logs, or error messages

Code Execution

  • RCE via deserialization, eval injection, XSS (reflected/stored/DOM)
  • Dynamic code execution with user-controlled input

Data Exposure

  • Sensitive data in logs, PII handling, API endpoint leakage, debug info
  • Information disclosure through error messages or stack traces

Prompt Injection

  • External content (web, API, user input) targeting AI without sanitization
  • Untrusted data used in prompts or AI instructions

Method

Trace data flow from user inputs → through processing → to sensitive operations. Flag where untrusted data crosses trust boundaries without validation.

For DEEP mode: include detailed exploit scenarios for every Critical finding.

False Positives (do NOT flag)

  • UUIDs as identifiers (assumed unguessable)
  • Environment variables / CLI flags (trusted values)
  • Framework default protections (React auto-escaping, Angular sanitization) unless explicitly bypassed
  • Client-side permission checks (not real security boundaries)
  • Logging non-PII data
  • DoS / rate limiting (out of scope for code review)
  • Pre-existing issues not introduced in the diff
  • Generated code, lockfiles, build output

Read the full file on GitHub · 112 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 · 112 lines · 73 tokens per session scan A d5cc03bf396d

Subscribe to this mod's changes

cf-reviewer-security is an agent published in the GitHub repository dinhanhthi/coding-friend (3 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 823 once invoked, about $0.0004 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.