security-auditor

A security review covering common ways applications can be attacked, including injection, weak login or permissions, exposed secrets, unsafe settings, cross-site request forgery, missing rate limits, and data leaks.

In plain words
What is it for?
Use it to inspect application code and configuration for OWASP Top 10-style issues, including SQL and script injection, authentication, access control, credentials, headers, CSRF, and data exposure.
Why use it?
It brings security checks into one audit and helps identify risks before attackers or accidental exposure cause harm.

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/undeadlist/claude-code-agents/security-auditor
Clone the repo
git clone --depth 1 https://github.com/undeadlist/claude-code-agents
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 2,728 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 2 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 $0.02728
Opus 5 $0.00012 $0.01364
Sonnet 5 $0.00005 $0.00546
Haiku 4.5 $0.00002 $0.00273

Measured 2d ago against content hash e44786d4792b, 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 2 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

const response = await fetch(req.query.url); // SSRF!

Runs shell commandslowCapability

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

grep -rn "exec\|spawn\|execSync" src --include="*.ts" | head -10
agents/security-auditor.md · 352 lines

How it starts

The opening of the file, as written. The whole thing — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Audit (Comprehensive)

Single source of truth for ALL security checks. Output to .claude/audits/AUDIT_SECURITY.md.

Status Block (Required)

Every output MUST start with:

---
agent: security-auditor
status: COMPLETE | PARTIAL | SKIPPED | ERROR
timestamp: [ISO timestamp]
duration: [seconds]
findings: [count]
critical_count: [count]
high_count: [count]
errors: []
skipped_checks: []
---

Scope (SINGLE AUTHORITY)

security-auditor is the ONLY agent that checks:

  • Injection attacks (SQL, NoSQL, Command, XSS, LDAP)
  • Authentication & session management
  • Authorization & access control
  • Secrets & credential exposure
  • Security headers & configuration
  • CSRF protection
  • Rate limiting
  • Data exposure risks

Other agents do NOT check security:

  • bug-auditor: Runtime bugs only (not security)
  • code-auditor: Code quality only (not security)

1. Injection Attacks

SQL Injection

# Raw queries with string interpolation
grep -rn "\$queryRaw\|\$executeRaw" src --include="*.ts" | head -10
grep -rn "query\s*(" src --include="*.ts" | grep -v "prisma\." | head -10
grep -rn '`.*\$\{.*\}.*`' src --include="*.ts" | grep -i "select\|insert\|update\|delete" | head -10

NoSQL Injection

# MongoDB query manipulation
grep -rn "\.find\s*(\s*{" src --include="*.ts" | head -10
grep -rn "\$where\|\$regex" src --include="*.ts" | head -5

Command Injection

# Shell command execution
grep -rn "exec\|spawn\|execSync" src --include="*.ts" | head -10
grep -rn "child_process" src --include="*.ts" | head -5

XSS (Cross-Site Scripting)

# Dangerous HTML rendering
grep -rn "dangerouslySetInnerHTML\|innerHTML\|outerHTML" src --include="*.tsx" --include="*.ts" | head -10
# Unsanitized output
grep -rn "\.html\s*(" src --include="*.ts" | head -5

2. Authentication & Session

# Unprotected API routes (no auth check)
grep -rn "export.*GET\|export.*POST" src/app/api --include="*.ts" | head -20

# Check for auth in routes
for file in $(find src/app/api -name "route.ts" 2>/dev/null); do
  grep -L "getServerSession\|auth\|verify\|middleware" "$file" 2>/dev/null
done | head -10

# Password handling
grep -rn "password" src --include="*.ts" | grep -v "hash\|bcrypt\|argon" | head -10

# Session configuration
grep -rn "maxAge\|expires\|secure\|httpOnly" src --include="*.ts" | head -10

Read the full file on GitHub · 352 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. 2d ago First seen · 352 lines · 24 tokens per session scan A e44786d4792b

Subscribe to this mod's changes

security-auditor is an agent published in the GitHub repository undeadlist/claude-code-agents (147 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 2,728 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.