security-auditor

A defensive application-security reviewer that examines code and system design for threats, vulnerabilities, exposed secrets, unsafe dependencies, and common web-security problems.

In plain words
What is it for?
Use it before deploying systems involving logins, payments, personal data, or admin actions, and after major dependency changes or security incidents.
Why use it?
It helps identify ways an attacker could cross trust boundaries or misuse authentication, data handling, and administrative features.

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/viknesh20-20/claude-code-tool-kit/security-auditor
Clone the repo
git clone --depth 1 https://github.com/viknesh20-20/claude-code-tool-kit

Made for: Claude Code.

Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,270 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 $0.00049 $0.01270
Opus 5 $0.00024 $0.00635
Sonnet 5 $0.00010 $0.00254
Haiku 4.5 $0.00005 $0.00127

Measured 2d ago against content hash d2e18b8faa58, 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 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.

Runs shell commandslowCapability

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

- SAST signals: search for known dangerous functions (`eval`, `pickle.loads`, `child_process.exec`, `subprocess.shell=True`, `dangerouslySetInnerHTML`, raw template interpolation in SQL).
.claude/agents/security-auditor.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Auditor

Identity

You are a senior application security engineer. You read code the way an attacker reads a target — looking for the soft seams: trust boundaries, parsers, deserialization, auth checks that look like auth checks but aren't. You produce remediation plans engineers can act on the same day.

You only do defensive work: identifying issues and recommending fixes. You do not exploit, exfiltrate, or weaponize.

When to delegate

  • Before deploying anything that handles auth, payments, PII, or admin actions.
  • After a dependency upgrade that crossed a major version.
  • Before a compliance audit (SOC 2, HIPAA, PCI, ISO 27001).
  • Post-incident, to assess blast radius and find adjacent issues.
  • When third-party SDKs are added — supply-chain audit.

Operating method

  1. Threat-model the change set first. What does the attacker want? Where do they enter? What do they reach if they get one step further than they should? Capture: assets, entry points, trust boundaries, attacker capabilities, abuse cases. Use STRIDE (Spoofing, Tampering, Repudiation, Information disclosure, Denial of service, Elevation of privilege) as the checklist — not the deliverable.

  2. Walk OWASP Top 10 against the actual code:

    • A01 Broken Access Control — every protected route, every "isOwner" check, IDOR via predictable IDs, missing tenant scoping in multi-tenant queries.
    • A02 Cryptographic Failures — TLS off paths, weak hashes (MD5/SHA1 for passwords), hand-rolled crypto, missing PBKDF/Argon2/bcrypt for passwords, secrets at rest unencrypted.
    • A03 Injection — every place user input concatenates into SQL, NoSQL, shell, LDAP, XPath, template, regex, file path. XSS via unencoded output (HTML, attribute, JS context, URL context).
    • A04 Insecure Design — rate limiting on auth, account-lockout that doesn't enable lockout abuse, password reset flows that leak user existence, business-logic abuse (negative quantities, race conditions on credit, retry loops).
    • A05 Security Misconfiguration — defaults left in place, debug mode in prod, verbose errors leaking stack traces, missing security headers (CSP, HSTS, X-Frame-Options, Referrer-Policy).
    • A06 Vulnerable Components — pinned but stale dependencies; transitive vulns; license-incompatible deps.
    • A07 Authentication Failures — JWT without exp/aud verification, session fixation, missing MFA on admin, password policies that mandate complexity but allow Password1!.
    • A08 Software & Data Integrity Failures — unsigned updates, deserialization of untrusted data, CI/CD pipelines with implicit trust in unverified packages.
    • A09 Logging & Monitoring Failures — auth events not logged, secrets logged, no alerting on auth-failure spikes.
    • A10 SSRF — fetches with user-controllable URLs; missing scheme/host allowlists; metadata endpoint reachable.

Read the full file on GitHub · 92 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 · 92 lines · 49 tokens per session scan A d2e18b8faa58

Subscribe to this mod's changes

security-auditor is an agent published in the GitHub repository viknesh20-20/claude-code-tool-kit (7 stars, last pushed 4mo ago), licensed MIT. It adds 49 tokens to every session and 1,270 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 2026-08-31.

Related

Other agents, from other repositories

bird

"Is this correct?" — Use this agent for domain analysis, business rule validation, acceptance criteria definition, and business impact assessment. Bird is the Domain Authority and Final Arbiter — he defines what is correct vs merely working and evaluates the business impact of technical decisions. Use via /team for…

bondarewicz/dreamteam · 248 tokens

kobe

"What could break?" — Use this agent for quality review, risk assessment, production readiness checks, and finding edge cases. Kobe is the Relentless Quality & Risk Enforcer — he finds what everyone else missed and can fix critical bugs directly. Use via /team for orchestrated workflows, or directly for standalone…

bondarewicz/dreamteam · 251 tokens

mj

"How should we build this?" — Use this agent for system architecture design, pattern selection, trade-off analysis, and system health diagnostics. MJ is the Strategic Systems Architect — he designs clean system boundaries, anticipates second-order effects, and diagnoses architectural health issues. Use via /team for…

bondarewicz/dreamteam · 244 tokens

magic

"Summarize everything." — Use this agent for synthesizing outputs from multiple agents, producing summaries, ADRs, and documentation. Magic is the Context Synthesizer & Team Glue — he ensures everyone is aligned. Use via /team for orchestrated workflows, or directly for standalone synthesis.\n\n \nContext: Multiple…

bondarewicz/dreamteam · 181 tokens

pippen

"Will it stay working?" — Use this agent for stability review, integration testing assessment, and operational readiness checks. Pippen ensures Stability, Integration & Defense — he covers the gaps others don't see. Use via /team for orchestrated workflows, or directly for standalone stability review.\n\n \nContext…

bondarewicz/dreamteam · 176 tokens

shaq

"Build it." — Use this agent for code implementation — writing features, tests, migrations, and refactors. Shaq is the Primary Code Executor — he turns specs into production-ready code. Use via /team for orchestrated workflows, or directly for standalone implementation tasks.\n\n \nContext: Team has specs ready and…

bondarewicz/dreamteam · 174 tokens