security-audit

security-audit is a skill for Claude Code, Codex from andrewvaughan/agent-council. It costs 51 tokens per session (2,852 once invoked), scanned A, original, MIT.

A code-focused security review that combines automated source-code scanning, STRIDE threat modeling, and attack-tree analysis. STRIDE is a method for considering common kinds of security threats.

In plain words
What is it for?
Auditing a whole codebase or selected directories, such as authentication, APIs, data protection, or frontend code. It produces a prioritized report with remediation steps after the audit scope is confirmed.
Why use it?
It helps identify application security weaknesses before releases or after sensitive changes. The stated review excludes infrastructure issues such as TLS, firewalls, DNS, and network layout.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is **Model Selection**: See the [Model Selection](../../README.md#model-selection) section in README.md for mapping agent model specs to Task tool parameters..

Good fit Auditing a whole codebase or selected directories, such as authentication, APIs, data protection, or frontend code. It produces a prioritized report with remediation steps after the audit scope is confirmed.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/andrewvaughan/agent-council
agentmods
npx agentmods add skills/andrewvaughan/agent-council/security-audit

Made for: Claude Code, Codex.

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-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/andrewvaughan/agent-council/security-audit/github.svg)](https://agentmods.dev/skills/andrewvaughan/agent-council/security-audit)
Your own site
<a href="https://agentmods.dev/skills/andrewvaughan/agent-council/security-audit"><img src="https://agentmods.dev/badge/skills/andrewvaughan/agent-council/security-audit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for security-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/andrewvaughan/agent-council/security-audit"><img src="https://agentmods.dev/badge/skills/andrewvaughan/agent-council/security-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,852 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00051 $0.02852
Opus 5 $0.00026 $0.01426
Sonnet 5 $0.00010 $0.00570
Haiku 4.5 $0.00005 $0.00285

Measured 9d ago against content hash ebb5b6e769cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

security-audit 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 9d 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.

canonical/skills/security-audit/SKILL.md · 320 lines

How it starts

The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Audit Workflow

Run a comprehensive security audit that combines automated static analysis, threat modeling, and multi-perspective council review. This skill produces a prioritized audit report with actionable remediation steps.

Scope Exclusions

[!IMPORTANT] This audit covers application-level security only. Production infrastructure (TLS termination, reverse proxy, network segmentation, firewall rules, DNS) is managed by a separate project and is out of scope. Do not flag missing TLS, reverse proxy configuration, network-level MITM risks, or production deployment topology as findings.

Step 1: Define Audit Scope

Ask the user:

  • Scope: Full codebase or specific area? (e.g., apps/api/src/auth/, apps/web/src/)
  • Trigger: What prompted this audit? (routine, pre-release, security incident, new feature, dependency update)
  • Focus areas: Authentication, API security, data protection, frontend security, or all?

CHECKPOINT: Confirm the audit scope and focus areas with the user before proceeding.

Step 2: Automated SAST Scanning

Invoke /security-scanning:security-sast on the defined scope.

Scan for:

  • Injection: SQL injection, NoSQL injection, command injection, LDAP injection
  • XSS: Reflected, stored, and DOM-based cross-site scripting
  • CSRF: Missing CSRF protections on state-changing endpoints
  • Authentication: Weak password policies, broken auth flows, session fixation
  • Secrets: Hardcoded API keys, passwords, tokens, connection strings
  • Dependencies: Known vulnerabilities in npm packages (CVEs)
  • Deserialization: Insecure deserialization patterns
  • Prototype pollution: JavaScript-specific object manipulation attacks

Collect every finding with:

  • Severity: Critical / High / Medium / Low / Info
  • Category: OWASP Top 10 mapping
  • Location: File path and line number
  • Description: What the vulnerability is
  • Evidence: The specific code pattern that triggered the finding
  • Remediation: How to fix it

Read the full file on GitHub · 320 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. 9d ago First seen · 320 lines · 51 tokens per session scan A ebb5b6e769cc

Subscribe to this mod's changes

security-audit is a skill published in the GitHub repository andrewvaughan/agent-council (13 stars, last pushed 6mo ago), licensed MIT. It adds 51 tokens to every session and 2,852 once invoked, about $0.0003 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.