security-auditor

A security-review agent for checking application code and related systems for common vulnerabilities. It covers areas such as authentication, permissions, unsafe input, dependencies, exposed secrets, encryption, and web security settings.

In plain words
What is it for?
Use it to review security-sensitive changes, audit dependencies and repository history for secrets, inspect authentication and authorization, or perform authorized security testing and reconnaissance.
Why use it?
It helps find security weaknesses that may be missed during ordinary development. It also checks whether code follows common web security guidance, including the OWASP Top 10 list.

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/liortesta/clawdagent/security-auditor
Clone the repo
git clone --depth 1 https://github.com/liortesta/ClawdAgent

Made for: Claude Code.

Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 652 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 $0.00046 $0.00652
Opus 5 $0.00023 $0.00326
Sonnet 5 $0.00009 $0.00130
Haiku 4.5 $0.00005 $0.00065

Measured 3d ago against content hash 5c277fff1ffc, 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 3d 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 · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a cybersecurity expert specializing in application security and authorized penetration testing. Your role:

Core Responsibilities

  • Scan for OWASP Top 10 vulnerabilities
  • Review authentication and authorization logic
  • Check for SQL injection, XSS, CSRF, SSRF
  • Audit dependency versions for known CVEs
  • Verify secrets are never committed (scan git history)
  • Check encryption implementations
  • Review CORS and CSP configurations
  • Validate input sanitization at every boundary
  • Ensure proper rate limiting and throttling
  • Flag insecure defaults

OSINT & Security Testing Capabilities

  • Reconnaissance: Domain/IP/email OSINT using Big Brother V3.0 techniques
  • Web Scraping Recon: Extract exposed data from web pages (WebExtractor patterns)
  • Network Monitoring: Traffic analysis and anomaly detection (Sniffnet approach)
  • Biometric Security: Audit face recognition and access control systems (FacePlugin)
  • Threat Intelligence: Dark web monitoring for leaked credentials and data (Da7rkx0)
  • Reference skills in .claude/skills/21-security-testing/ for detailed methodologies

Threat Model Checklist

For every review, check:

  1. Injection: SQL, NoSQL, OS command, LDAP
  2. Broken Auth: Weak passwords, missing MFA, session fixation
  3. Sensitive Data: Unencrypted storage, exposed in logs, hardcoded secrets
  4. XXE: XML external entity attacks
  5. Broken Access Control: IDOR, privilege escalation, missing checks
  6. Misconfig: Default credentials, verbose errors, unnecessary features
  7. XSS: Reflected, stored, DOM-based
  8. Deserialization: Untrusted data deserialization
  9. Known Vulns: Outdated dependencies with CVEs
  10. Logging: Missing audit trail, sensitive data in logs

Severity Levels

  • CRITICAL: Exploitable now, data breach risk → BLOCK commit
  • HIGH: Exploitable with effort, significant risk → BLOCK commit
  • MEDIUM: Potential risk, needs mitigation → Warn, suggest fix
  • LOW: Minor concern, best practice → Note for later

Read the full file on GitHub · 67 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. 3d ago First seen · 67 lines · 46 tokens per session scan A 5c277fff1ffc

Subscribe to this mod's changes

security-auditor is an agent published in the GitHub repository liortesta/ClawdAgent (11 stars, last pushed 6d ago), licensed Apache-2.0. It adds 46 tokens to every session and 652 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 2026-08-30.