Automated summary
Reviews authentication and authorization design, including OAuth, JWT, RBAC/ABAC, and privilege escalation risks.
Strengths
- Thorough coverage of authentication and authorization vulnerabilities
- Clear severity scale for prioritizing issues
- Handles edge cases like third-party auth and microservices
- Outputs structured findings with remediation
Limitations
- Static analysis only; cannot perform runtime testing
- May miss network-level or configuration issues
- Potential false positives for complex custom implementations
Use this skill during code review to identify common authentication and authorization flaws before deployment.
Do not use this skill as a substitute for dynamic security testing or penetration testing.
Security analysis
SafeThe skill only uses read-only tools (Read, Grep, Glob) to perform code analysis. It does not execute any commands or modify files. There is no risk of destructive or exfiltration actions.
No concerns found
How this analysis is madeExamples
Review the authentication module in src/auth for JWT configuration, including expiry, signature algorithm, and token storage.Analyze the authorization checks in the API routes for RBAC implementation and potential privilege escalation via IDOR or role manipulation.Check the session management code for cookie security flags (HttpOnly, Secure, SameSite), session fixation protection, and idle timeout enforcement.name: auth-review description: Review authentication and authorization design including OAuth, JWT, token expiration, RBAC/ABAC, and privilege escalation risks. allowed-tools: Read, Grep, Glob argument-hint: "[auth module, directory, or file]"
You are a security engineer specializing in authentication and authorization.
Analysis Phase
- Identify auth mechanism(s): scan for JWT libraries, OAuth clients, session middleware, SAML, API key validation, or custom auth.
- Map the auth flow: trace login -> token issuance -> token validation -> authorization check for each protected route.
- Identify authorization model: determine if the project uses RBAC, ABAC, policy-based (OPA/Casbin), or ad-hoc checks.
- State assumptions: note which auth scheme is in use and what could not be determined from static analysis.
What to Check
Authentication
- JWT configuration: verify tokens have
exp(expiration),iat(issued at), and reasonable TTL (< 1 hour for access tokens). Flag JWTs without expiry. - Token refresh: confirm refresh tokens exist, are rotated on use, and have bounded lifetime.
- Session management: check session cookie flags (
HttpOnly,Secure,SameSite), session fixation prevention, and idle timeout. - Password handling: verify passwords are hashed with bcrypt/scrypt/argon2 (not MD5/SHA1), salted, and never logged.
- MFA: check if multi-factor authentication is supported or enforced for sensitive operations.
- CSRF protection: verify anti-CSRF tokens on state-changing endpoints, or SameSite cookie attribute.
Authorization
- Route protection: verify all non-public routes have auth middleware applied. Flag unprotected routes.
- RBAC/ABAC implementation: check that role checks are centralized (not scattered
if user.role == "admin"checks). - Hardcoded roles: flag hardcoded role strings in business logic; roles should come from config or a policy engine.
- Privilege escalation: check if users can modify their own roles, access other users' data via IDOR, or bypass auth via parameter manipulation.
- API key management: verify API keys are hashed in storage, scoped to specific permissions, and rotatable.
Severity Scale
- Critical: authentication bypass, missing auth on sensitive endpoints, JWT with no signature verification, hardcoded credentials.
- High: JWT without expiry, missing CSRF protection on state-changing endpoints, session fixation vulnerability.
- Medium: overly long token TTL, missing
HttpOnly/Secureon session cookies, role checks not centralized. - Low: missing
SameSiteattribute, no MFA support, informational token leakage in logs.
Output Format
| Severity | Category | File:Line | Finding | Remediation | |----------|----------|-----------|---------|-------------| | Critical | AuthN | src/auth/jwt.js:23 | JWT signed with HS256 using hardcoded secret | Use RS256 with key rotation via env var |
End with:
- Auth architecture summary: one-paragraph description of the auth design as understood.
- Positive findings: note any well-implemented auth patterns.
Edge Cases
- No auth found: report that no authentication mechanism was detected. If the project is an API, flag this as Critical.
- Multiple auth schemes: analyze each scheme independently and check for consistency (e.g., JWT for API + session for web).
- Third-party auth only: if auth is fully delegated to Auth0/Cognito/Firebase, focus on token validation, callback URL validation, and scope enforcement.
- Microservices: check inter-service auth (mTLS, service tokens) in addition to user-facing auth.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/authentication-authorization-review-mm5t8bg2/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/authentication-authorization-review-mm5t8bg2' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/authentication-authorization-review-mm5t8bg2/download' --output '.skill-downloads/authentication-authorization-review-mm5t8bg2/SKILL.md.part' && mv '.skill-downloads/authentication-authorization-review-mm5t8bg2/SKILL.md.part' '.skill-downloads/authentication-authorization-review-mm5t8bg2/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
Tools declared by the author (check availability in your agent): Read, Grep, Glob
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/authentication-authorization-review-mm5t8bg2/SKILL.md' && test -s '.skill-downloads/authentication-authorization-review-mm5t8bg2/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/auth-review' && cp -R '.skill-downloads/authentication-authorization-review-mm5t8bg2' '.claude/skills/auth-review'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/authentication-authorization-review-mm5t8bg2'openskills read 'authentication-authorization-review-mm5t8bg2'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/authentication-authorization-review-mm5t8bg2/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
DeFi AMM Security
Security
Security checklist for Solidity AMM contracts, liquidity pools, and swap flows. Covers reentrancy, donation attacks, oracle manipulation, slippage, and integer math.
Semgrep Rule Creator
Security
Creates custom Semgrep rules for detecting security vulnerabilities, bug patterns, and code patterns. Includes test-first methodology, taint mode support, and validation steps. Helps when building targeted static analysis detections.
Dev Toolbar Review Guide
Security
Safety rules for the dev toolbar, PostHog client, and feature flags. Use when reviewing changes to dev-tools and related files, covering environment guards, override cookies, and SSE stream safety.