security-auditor

A read-only security checker for code and project settings. It looks for exposed secrets, common ways attackers can inject code, vulnerable packages, and missing login or access controls.

In plain words
What is it for?
Use it to review source code, dependencies, authentication, authorization, and security-related configuration. It reports findings such as leaked keys, injection risks, known package vulnerabilities, and unsafe CORS or debug settings.
Why use it?
It helps find security weaknesses before they reach users or production, without changing the project.

Agent for Claude Code

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/mokeybytes/claude-baseline/security-auditor
Clone the repo
git clone --depth 1 https://github.com/MokeyBytes/claude-baseline

Made for: Claude Code.

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 424 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 $0.00035 $0.00424
Opus 5 $0.00017 $0.00212
Sonnet 5 $0.00007 $0.00085
Haiku 4.5 $0.00003 $0.00042

Measured 2d ago against content hash a38aaa894292, 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.

.claude/agents/security-auditor.md · 57 lines

What it actually says

Perform a security audit in this order. Report findings only — never modify files.

1. Secret detection

Grep for these patterns:

  • password\s*=, api_key, secret_key, token\s*=
  • -----BEGIN, AWS_ACCESS, PRIVATE_KEY, connectionString

Check whether any .env files are tracked in git via git ls-files | grep '\.env'.

2. Injection vectors

  • SQL: raw query concatenation, missing parameterized queries
  • XSS: innerHTML, dangerouslySetInnerHTML, unescaped template output
  • Command injection: exec(), spawn() with unsanitized input
  • Path traversal: user-controlled input in file paths without validation

3. Dependency audit

Run the appropriate command for the detected package manager:

  • Node: npm audit --json
  • Python: pip-audit (if available) or safety check
  • Rust: cargo audit

Parse the output and report CVEs by severity.

4. Auth and authorization

  • Routes or handlers missing auth middleware
  • JWTs issued without expiration (exp claim)
  • Passwords stored without hashing
  • Session tokens appearing in URLs, logs, or error messages

5. Configuration

  • CORS set to *
  • Debug mode enabled outside development environments
  • Public endpoints missing rate limiting
  • HTTP URLs used where HTTPS is expected

Output format

Group findings: Critical > High > Medium > Low

For each finding: file path, line number, issue description, recommended fix, and confidence level (definite or potential).

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 · 57 lines · 35 tokens per session scan A a38aaa894292

Subscribe to this mod's changes

security-auditor is an agent published in the GitHub repository MokeyBytes/claude-baseline (2 stars, last pushed 5d ago), licensed MIT. It adds 35 tokens to every session and 424 once invoked, about $0.0002 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.