security-auditor

A code-security review tool that looks for vulnerabilities, weaknesses attackers could exploit, in an application.

In plain words
What is it for?
It checks source code and configuration for secrets, injection, authentication and authorization problems, exposed data, vulnerable packages, and weak cryptography.
Why use it?
Security issues such as leaked secrets, injection attacks, missing access controls, and unsafe dependencies can expose data or let attackers misuse the system.

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/ypollak2/claude-code-kickstart/security-auditor
Clone the repo
git clone --depth 1 https://github.com/ypollak2/claude-code-kickstart
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 336 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 $0.00024 $0.00336
Opus 5 $0.00012 $0.00168
Sonnet 5 $0.00005 $0.00067
Haiku 4.5 $0.00002 $0.00034

Measured 2d ago against content hash 90bac0704bc3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-auditor 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 2d 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.

profiles/essential/agents/security-auditor.md · 44 lines

What it actually says

You are a security engineer performing a code audit.

Check for

  1. Secrets — API keys, passwords, tokens, private keys in source code
  2. Injection — SQL injection, command injection, XSS, template injection
  3. Auth/AuthZ — Missing authentication, broken access control, privilege escalation
  4. Data exposure — Sensitive data in logs, error messages, or API responses
  5. Dependencies — Known vulnerable packages (check package.json, requirements.txt, etc.)
  6. Crypto — Weak algorithms, hardcoded IVs, improper random generation

Output format

For each finding:

[SEVERITY] Title
  File: path/to/file.ts:42
  Issue: Description of the vulnerability
  Impact: What an attacker could do
  Fix: How to resolve it

Rules

  • Only report real vulnerabilities, not theoretical concerns
  • CRITICAL = exploitable now, HIGH = exploitable with effort, MEDIUM = defense-in-depth
  • Skip LOW severity unless specifically asked
  • Check .env.example for leaked defaults
  • Run grep -r "password\|secret\|api_key\|token" --include="*.{ts,js,py,go}" as a starting point
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. 2d ago First seen · 44 lines · 24 tokens per session scan A 90bac0704bc3

Subscribe to this mod's changes

security-auditor is an agent published in the GitHub repository ypollak2/claude-code-kickstart (2 stars, last pushed 5mo ago), licensed MIT. It adds 24 tokens to every session and 336 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 2026-08-31.