/auth-audit
Use when auditing JWT, session, OAuth2/PKCE, password, or MFA implementations for security vulnerabilities and best-practice deviations.
$ npx -y skills add fusengine/agents --skill auth-audit --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/auth-audit
Context preview
The summary Claude sees to decide when to auto-load this skill.
Use when auditing JWT, session, OAuth2/PKCE, password, or MFA implementations for security vulnerabilities and best-practice deviations.
SKILL.md
auth-audit.SKILL.mdname: auth-audit
description: "Use when auditing JWT, session, OAuth2/PKCE, password, or MFA implementations for security vulnerabilities and best-practice deviations."
argument-hint: "[--jwt] [--session] [--oauth]"
user-invocable: true
<objective> This skill audits authentication and authorization implementations end to end: JWT signing algorithm, expiration, refresh, and storage; session storage, expiry, regeneration, and fixation; OAuth2 PKCE, state parameter, and redirect validation; password hashing algorithm, strength rules, and reset flow; and MFA implementation, backup codes, and recovery.
It runs a fixed workflow — detect the auth implementation, scan for known anti-patterns, verify cryptographic choices, check token/session lifecycle, and audit authorization logic (RBAC/ABAC) — checking for vulnerabilities such as JWT signed with `none`, undersized JWT secrets, missing/too-long token expiration, refresh tokens in localStorage, session fixation, missing CSRF protection, and OAuth flows missing PKCE or the `state` parameter. </objective>
Auth Audit Skill
Overview
Comprehensive audit of authentication and authorization implementations.
Audit Categories
| Category | Checks | |----------|--------| | JWT | Signing algo, expiration, refresh, storage | | Sessions | Storage, expiry, regeneration, fixation | | OAuth2 | PKCE, state param, redirect validation | | Passwords | Hashing algo, strength rules, reset flow | | MFA | Implementation, backup codes, recovery |
Workflow
1. **Detect** auth implementation (JWT, sessions, OAuth) 2. **Scan** for known anti-patterns 3. **Verify** cryptographic choices 4. **Check** token/session lifecycle 5. **Audit** authorization logic (RBAC, ABAC)
Common Vulnerabilities
- JWT signed with `none` algorithm
- JWT secret too short (< 256 bits)
- No token expiration or too long
- Refresh tokens stored in localStorage
- Session fixation after login
- Missing CSRF protection
- OAuth without PKCE for public clients
- Missing `state` parameter in OAuth flow
References
- [Auth Patterns](references/auth-patterns.md)
- [Auth Checklist](references/templates/auth-checklist.md)
Read more
name: auth-audit description: "Use when auditing JWT, session, OAuth2/PKCE, password, or MFA implementations for security vulnerabilities and best-practice deviations." argument-hint: "[--jwt] [--session] [--oauth]" user-invocable: true
<objective> This skill audits authentication and authorization implementations end to end: JWT signing algorithm, expiration, refresh, and storage; session storage, expiry, regeneration, and fixation; OAuth2 PKCE, state parameter, and redirect validation; password hashing algorithm, strength rules, and reset flow; and MFA implementation, backup codes, and recovery.
It runs a fixed workflow — detect the auth implementation, scan for known anti-patterns, verify cryptographic choices, check token/session lifecycle, and audit authorization logic (RBAC/ABAC) — checking for vulnerabilities such as JWT signed with `none`, undersized JWT secrets, missing/too-long token expiration, refresh tokens in localStorage, session fixation, missing CSRF protection, and OAuth flows missing PKCE or the `state` parameter. </objective>
Auth Audit Skill
Overview
Comprehensive audit of authentication and authorization implementations.
Audit Categories
| Category | Checks | |----------|--------| | JWT | Signing algo, expiration, refresh, storage | | Sessions | Storage, expiry, regeneration, fixation | | OAuth2 | PKCE, state param, redirect validation | | Passwords | Hashing algo, strength rules, reset flow | | MFA | Implementation, backup codes, recovery |
Workflow
1. **Detect** auth implementation (JWT, sessions, OAuth) 2. **Scan** for known anti-patterns 3. **Verify** cryptographic choices 4. **Check** token/session lifecycle 5. **Audit** authorization logic (RBAC, ABAC)
Common Vulnerabilities
- JWT signed with `none` algorithm
- JWT secret too short (< 256 bits)
- No token expiration or too long
- Refresh tokens stored in localStorage
- Session fixation after login
- Missing CSRF protection
- OAuth without PKCE for public clients
- Missing `state` parameter in OAuth flow
References
- [Auth Patterns](references/auth-patterns.md)
- [Auth Checklist](references/templates/auth-checklist.md)
A plugin ecosystem that turns Claude Code into a supervised, multi-agent development environment.
Repo: fusengine/agents
Other skills on fusengine-agents.
- /agent-creator
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
Open skill - /apex-methodology
Use when starting ANY development task -- feature, bug fix, refactor, hotfix (triggers: implement, create, build, fix, add feature, refactor, develop).
Open skill - /brainstorming
Use when creating a feature/component or adding functionality. Fires BEFORE APEX Analyze to refine requirements via structured questioning.
Open skill - /challenge
Use before a root-cause, done/verified claim, irreversible action, or 2nd-time fix reaches the owner (APEX or plain conversation); also fires at every eLicit/Verify gate. Not for code correctness (use sniper).
Open skill - /code-quality
Use when validating code quality after modifications -- SOLID compliance, DRY duplication, linter errors, architecture violations. Do NOT use for functional verification (run verification FIRST, then code-quality).
Open skill - /elicitation
Use when an expert agent self-reviews and self-corrects code after the Execute phase, before sniper validation (BMAD-METHOD elicitation techniques).
Open skill

