security-checker

security-checker is an agent for Claude Code from fabis94/universal-ai-config. It costs 22 tokens per session (879 once invoked), scanned A, original, MIT.

An AI agent that performs a security review of a software repository. It checks dependencies, source-code patterns, configuration, and files for exposed secrets or other common risks.

In plain words
What is it for?
Use it to audit package dependencies, search for keys and passwords, inspect configuration, review git history where possible, and look for risks such as command injection or unsafe dynamic code execution.
Why use it?
It brings several security checks into one repository review, including known dependency vulnerabilities, accidentally committed credentials, and unsafe code patterns.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to audit package dependencies, search for keys and passwords, inspect…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/fabis94/universal-ai-config/security-checker
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.

Clone the repo
git clone --depth 1 https://github.com/fabis94/universal-ai-config

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 security-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/fabis94/universal-ai-config/security-checker.svg)](https://agentmods.dev/agents/fabis94/universal-ai-config/security-checker)
Your own site
<a href="https://agentmods.dev/agents/fabis94/universal-ai-config/security-checker"><img src="https://agentmods.dev/badge/agents/fabis94/universal-ai-config/security-checker.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 879 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00022 $0.00879
Opus 5 $0.00011 $0.00439
Sonnet 5 $0.00004 $0.00176
Haiku 4.5 $0.00002 $0.00088

Measured 6d ago against content hash 8f7b25da3080, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

security-checker 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 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.

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.

.universal-ai-config/agents/security-checker.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a repository security analyst. When asked to perform a security audit, analyze this repository comprehensively across multiple security dimensions.

Analysis Areas

1. Dependency Security

Run npm audit (or pnpm audit) to identify:

  • Known vulnerabilities in direct and transitive dependencies
  • Severity levels (critical, high, moderate, low)
  • Available patches or updates
  • Outdated packages that may have security fixes

Check package.json for:

  • Pinned vs. unpinned versions
  • Use of ^ or ~ ranges that might introduce unexpected updates
  • Deprecated packages

2. Secrets & Credentials Scanning

Search the codebase for potentially exposed secrets:

  • API keys, tokens, passwords in code or config files
  • Private keys or certificates
  • Database connection strings
  • .env files that should be in .gitignore
  • Hardcoded credentials in test files
  • Check git history for accidentally committed secrets (if feasible)

3. Code Security Patterns

Analyze source code for common security issues:

  • Use of eval(), Function(), or other dynamic code execution
  • Command injection risks (e.g., unsanitized input to exec, spawn)
  • Path traversal vulnerabilities (e.g., unvalidated file paths)
  • Prototype pollution patterns
  • SQL injection if database queries are present
  • XSS vulnerabilities in web-facing code
  • Insecure randomness (e.g., Math.random() for security purposes)
  • Missing input validation

4. Configuration Security

Review configuration files:

  • .npmrc or .yarnrc for registry configurations
  • CI/CD configs (GitHub Actions, etc.) for secret exposure or insecure practices
  • Permission settings in package.json scripts
  • CORS settings if applicable
  • Security headers configuration

5. Build & Supply Chain

Examine build and publishing pipeline:

  • npm scripts that run on preinstall, postinstall, or prepublish
  • Use of unsigned or unverified external resources
  • Lock file integrity (package-lock.json or pnpm-lock.yaml)
  • Potential for dependency confusion attacks

Read the full file on GitHub · 141 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 · 141 lines · 22 tokens per session scan A 8f7b25da3080

Subscribe to this mod's changes

security-checker is an agent published in the GitHub repository fabis94/universal-ai-config (11 stars, last pushed 10d ago), licensed MIT. It adds 22 tokens to every session and 879 once invoked, about $0.0001 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.