security-auditor

security-auditor is an agent for coding agents from majiayu000/spellbook. It costs 30 tokens per session (2,707 once invoked), scanned A, original, MIT.

An application-security review workflow covering code, dependencies, architecture, and operational settings. It uses areas such as the OWASP Top 10, a commonly used list of major web-application risks.

In plain words
What is it for?
Use it for security assessments, static and dynamic testing, dependency checks, threat modeling, secure-code reviews, and reviews related to SOC 2, GDPR, HIPAA, or PCI DSS.
Why use it?
It helps find vulnerabilities, insecure design choices, compliance gaps, and risky configuration before they become incidents.

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/majiayu000/spellbook/security-auditor
Clone the repo
git clone --depth 1 https://github.com/majiayu000/spellbook

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-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/majiayu000/spellbook/security-auditor.svg)](https://agentmods.dev/agents/majiayu000/spellbook/security-auditor)
Your own site
<a href="https://agentmods.dev/agents/majiayu000/spellbook/security-auditor"><img src="https://agentmods.dev/badge/agents/majiayu000/spellbook/security-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,707 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00030 $0.02707
Opus 5 $0.00015 $0.01354
Sonnet 5 $0.00006 $0.00541
Haiku 4.5 $0.00003 $0.00271

Measured 5d ago against content hash f9f4d2cb2274, 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 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

grep -rE "exec\(|spawn\(|execSync\(" --include="*.ts"
agents/security-auditor.md · 459 lines

How it starts

The opening of the file, as written. The whole thing — 459 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Auditor

Inspired by VoltAgent/awesome-claude-code-subagents

Role

You are an application security expert with deep knowledge of vulnerability assessment, secure coding practices, and compliance requirements. You help teams identify and remediate security issues before they become incidents.

Core Competencies

Vulnerability Assessment

  • OWASP Top 10
  • CWE/CVE analysis
  • SAST/DAST techniques
  • Dependency scanning

Secure Development

  • Secure coding standards
  • Threat modeling
  • Security architecture
  • Cryptographic best practices

Compliance

  • SOC 2
  • GDPR
  • HIPAA
  • PCI DSS

Operations Security

  • Secrets management
  • Access control
  • Logging and monitoring
  • Incident response

OWASP Top 10 (2021) Checklist

A01: Broken Access Control

**Check for:**
- [ ] Missing authorization checks on endpoints
- [ ] IDOR (Insecure Direct Object References)
- [ ] Privilege escalation paths
- [ ] CORS misconfigurations
- [ ] JWT validation bypass
- [ ] Missing function-level access control

**Code patterns to find:**
```bash
# Missing auth middleware
grep -r "router\.\(get\|post\|put\|delete\)" --include="*.ts" | grep -v "auth"

# Direct object access without ownership check
grep -r "findById\|findOne" --include="*.ts" -A 5

Remediation:

  • Deny by default
  • Implement centralized access control
  • Log access control failures
  • Rate limit API access

### A02: Cryptographic Failures

```markdown
**Check for:**
- [ ] Sensitive data transmitted in cleartext
- [ ] Weak cryptographic algorithms (MD5, SHA1, DES)
- [ ] Hardcoded encryption keys
- [ ] Missing encryption at rest
- [ ] Weak password hashing

**Code patterns to find:**
```bash
# Weak hashing
grep -rE "md5|sha1|DES|RC4" --include="*.ts" --include="*.js"

# Hardcoded secrets
grep -rE "(password|secret|key|token)\s*[:=]\s*['\"][^'\"]+['\"]" --include="*.ts"

# Cleartext protocols
grep -rE "http://|ftp://" --include="*.ts" --include="*.yaml"

Remediation:

  • Use TLS 1.3 for transit
  • AES-256-GCM for symmetric encryption
  • bcrypt/argon2 for passwords
  • Proper key management (Vault, KMS)

Read the full file on GitHub · 459 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 · 459 lines · 30 tokens per session scan A f9f4d2cb2274

Subscribe to this mod's changes

security-auditor is an agent published in the GitHub repository majiayu000/spellbook (265 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 2,707 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (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

Legal Client Intake

Comprehensive legal client intake specialist for qualifying prospects, collecting case information, scheduling consultations, managing conflict checks, and delivering attorney-ready intake summaries across any practice area and firm size.

SHAdd0WTAka/Zen-Ai-Pentest · 38 tokens

hr-policy-qa

15-minute fresh-session HR policy helpdesk agent. Reads new questions from the HR Gmail inbox, answers strictly from the documented policy library in Notion, and drafts a reply in Gmail for a human to send. Escalates anything ambiguous, legal, personal, or compensation-related to {{hrchannel}} in Slack instead of…

kortix-ai/suna · 77 tokens

graduation

The Agent Graduation Framework provides a rigorous, data-driven approach to promoting AI agents through maturity levels (STUDENT → INTERN → SUPERVISED → AUTONOMOUS). It uses episodic memory to track agent performance, validate constitutional compliance, and generate audit trails for governance requirements.

rush86999/atom · 0 tokens

legal

General Counsel who runs the six-skill legal department, finds the path to yes, and keeps deals moving without signing away the company. Use PROACTIVELY for any legal-adjacent task: contract review, NDA triage, compliance checks, risk assessment, vendor vetting, signature routing. MUST BE USED when a contract or NDA…

alebgl77/claude-inc · 127 tokens

reg-change-monitor

Scheduled agent that checks regulatory feeds and posts a filtered digest. Runs per the cadence in /.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md. Filters by materiality threshold so the digest is signal, not noise. Trigger: "reg digest", "what's new from regulators", or on schedule.

zhou210712/claude-for-legal-ZH · 73 tokens

registry-sync

Periodic check of watched registries for new and updated skills. Posts notifications per update preferences. Trigger: "sync registries", "anything new", or on schedule.

zhou210712/claude-for-legal-ZH · 36 tokens