auth-audit

A command that scans an application's authentication and authorization code for security problems. Authentication checks who a user is; authorization checks what that user is allowed to do.

In plain words
What is it for?
Use `/auth-audit` to review JWT, session, OAuth, role-based access, or all supported authentication areas.
Why use it?
It helps find weaknesses in JWTs, sessions, OAuth, roles, permissions, and related access controls.

Command

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 commands/iwritec0de/app-dev/auth-audit
Clone the repo
git clone --depth 1 https://github.com/iwritec0de/app-dev
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,020 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 $0.00008 $0.01020
Opus 5 $0.00004 $0.00510
Sonnet 5 $0.00002 $0.00204
Haiku 4.5 $0.00001 $0.00102

Measured yesterday against content hash 9043e7dfa02f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

auth-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 yesterday.

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.

commands/auth-audit.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auth Audit

Scan the project's authentication and authorization implementation for security vulnerabilities.

Load the auth-patterns skill for authentication and authorization security patterns.

Usage

/auth-audit [--focus jwt|session|oauth|rbac|all]

Arguments

Parse $ARGUMENTS to extract:

  • --focus (optional, default: all)
    • jwt — JWT implementation issues
    • session — Session management issues
    • oauth — OAuth2 implementation issues
    • rbac — Role/permission issues
    • all — Audit everything

Instructions

1. Detect Auth Implementation

Search for auth patterns:

grep -rn "jsonwebtoken\|jose\|jwt\|JWT" --include="*.ts" --include="*.js" 2>/dev/null
grep -rn "bcrypt\|argon2\|scrypt\|pbkdf2" --include="*.ts" --include="*.js" 2>/dev/null
grep -rn "passport\|next-auth\|lucia\|clerk\|auth0\|supabase.*auth" --include="*.ts" --include="*.js" 2>/dev/null
grep -rn "session\|cookie\|Set-Cookie" --include="*.ts" --include="*.js" 2>/dev/null
grep -rn "role\|permission\|authorize\|canAccess\|isAdmin" --include="*.ts" --include="*.js" 2>/dev/null

2. JWT Audit

If JWT is used, check for:

Critical:

  • Weak or hardcoded secret key (secret in source code, short key, "secret")
  • Algorithm confusion (accepting none, not verifying alg header)
  • Missing token expiration (exp claim)
  • Token stored in localStorage (XSS-accessible)
  • Secret in client-side code

High:

  • No token refresh mechanism (long-lived access tokens)
  • Missing iss (issuer) validation
  • Missing aud (audience) validation
  • Token not invalidated on password change
  • No token revocation mechanism (logout doesn't invalidate)

Medium:

  • Using HS256 when RS256 is more appropriate (multi-service)
  • Excessive token payload (PII, roles should be verified server-side)
  • Missing jti for token uniqueness

3. Password Audit

Check for:

  • Weak hashing (MD5, SHA1, SHA256 without salt)
  • Missing salt (even with bcrypt, verify rounds ≥ 10)
  • Password stored in plaintext
  • No minimum password requirements enforced
  • Missing rate limiting on login endpoint
  • Missing account lockout after failed attempts
  • Password comparison using === instead of timing-safe compare

Read the full file on GitHub · 130 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. yesterday First seen · 130 lines · 8 tokens per session scan A 9043e7dfa02f

Subscribe to this mod's changes

auth-audit is a command published in the GitHub repository iwritec0de/app-dev (3 stars, last pushed 4mo ago), licensed MIT. It adds 8 tokens to every session and 1,020 once invoked, about $0.0000 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 2026-08-31.