鱼皮AI导航
鱼皮AI导航
  • 主页
  • 社区
  • AI工具
  • AI知识库
  • AI提示词
  • MCP
  • Skills
  • AI学习资源
  • AI资讯
  • GitHub开源
登录/注册

broken-authentication

面向 Web 应用的身份认证与会话安全评估,覆盖密码策略合规性、账号枚举识别、暴力破解与凭证填充测试、会话令牌随机性及超时机制验证、会话固定漏洞探测、多因素认证绕过分析,以及密码重置流程安全性审查。

测试与安全
访问 GitHub
文档Skills.MD
name
Broken Authentication Testing
description
This skill should be used when the user asks to "test for broken authentication vulnerabilities", "assess session management security", "perform credential stuffing tests", "evaluate password policies", "test for session fixation", or "identify authentication bypass flaws". It provides comprehensive techniques for identifying authentication and session management weaknesses in web applications.
metadata{"author":"zebbern","version":"1.1"}

Broken Authentication Testing

Purpose

Identify and exploit authentication and session management vulnerabilities in web applications. Broken authentication consistently ranks in the OWASP Top 10 and can lead to account takeover, identity theft, and unauthorized access to sensitive systems. This skill covers testing methodologies for password policies, session handling, multi-factor authentication, and credential management.

Prerequisites

Required Knowledge

  • HTTP protocol and session mechanisms
  • Authentication types (SFA, 2FA, MFA)
  • Cookie and token handling
  • Common authentication frameworks

Required Tools

  • Burp Suite Professional or Community
  • Hydra or similar brute-force tools
  • Custom wordlists for credential testing
  • Browser developer tools

Required Access

  • Target application URL
  • Test account credentials
  • Written authorization for testing

Outputs and Deliverables

  1. Authentication Assessment Report - Document all identified vulnerabilities
  2. Credential Testing Results - Brute-force and dictionary attack outcomes
  3. Session Security Analysis - Token randomness and timeout evaluation
  4. Remediation Recommendations - Security hardening guidance

Core Workflow

Phase 1: Authentication Mechanism Analysis

Understand the application's authentication architecture:

▼
text
复制代码
# Identify authentication type - Password-based (forms, basic auth, digest) - Token-based (JWT, OAuth, API keys) - Certificate-based (mutual TLS) - Multi-factor (SMS, TOTP, hardware tokens) # Map authentication endpoints /login, /signin, /authenticate /register, /signup /forgot-password, /reset-password /logout, /signout /api/auth/*, /oauth/*

Capture and analyze authentication requests:

▼
http
复制代码
POST /login HTTP/1.1 Host: target.com Content-Type: application/x-www-form-urlencoded username=test&password=test123

Phase 2: Password Policy Testing

Evaluate password requirements and enforcement:

▼
bash
复制代码
# Test minimum length (a, ab, abcdefgh) # Test complexity (password, password1, Password1!) # Test common weak passwords (123456, password, qwerty, admin) # Test username as password (admin/admin, test/test)

Document policy gaps: Minimum length <8, no complexity, common passwords allowed, username as password.

Phase 3: Credential Enumeration

Test for username enumeration vulnerabilities:

▼
bash
复制代码
# Compare responses for valid vs invalid usernames # Invalid: "Invalid username" vs Valid: "Invalid password" # Check timing differences, response codes, registration messages

Password reset

"Email sent if account exists" (secure) "No account with that email" (leaks info)

API responses

{"error": "user_not_found"} {"error": "invalid_password"}

▼
text
复制代码
### Phase 4: Brute Force Testing Test account lockout and rate limiting: ```bash # Using Hydra for form-based auth hydra -l admin -P /usr/share/wordlists/rockyou.txt \ target.com http-post-form \ "/login:username=^USER^&password=^PASS^:Invalid credentials" # Using Burp Intruder 1. Capture login request 2. Send to Intruder 3. Set payload positions on password field 4. Load wordlist 5. Start attack 6. Analyze response lengths/codes

Check for protections:

▼
bash
复制代码
# Account lockout - After how many attempts? - Duration of lockout? - Lockout notification? # Rate limiting - Requests per minute limit? - IP-based or account-based? - Bypass via headers (X-Forwarded-For)? # CAPTCHA - After failed attempts? - Easily bypassable?

Phase 5: Credential Stuffing

Test with known breached credentials:

▼
bash
复制代码
# Credential stuffing differs from brute force # Uses known email:password pairs from breaches # Using Burp Intruder with Pitchfork attack 1. Set username and password as positions 2. Load email list as payload 1 3. Load password list as payload 2 (matched pairs) 4. Analyze for successful logins # Detection evasion - Slow request rate - Rotate source IPs - Randomize user agents - Add delays between attempts

Phase 6: Session Management Testing

Analyze session token security:

▼
bash
复制代码
# Capture session cookie Cookie: SESSIONID=abc123def456 # Test token characteristics 1. Entropy - Is it random enough? 2. Length - Sufficient length (128+ bits)? 3. Predictability - Sequential patterns? 4. Secure flags - HttpOnly, Secure, SameSite?

Session token analysis:

▼
python
复制代码
#!/usr/bin/env python3 import requests import hashlib # Collect multiple session tokens tokens = [] for i in range(100): response = requests.get("https://target.com/login") token = response.cookies.get("SESSIONID") tokens.append(token) # Analyze for patterns # Check for sequential increments # Calculate entropy # Look for timestamp components

Phase 7: Session Fixation Testing

Test if session is regenerated after authentication:

▼
bash
复制代码
# Step 1: Get session before login GET /login HTTP/1.1 Response: Set-Cookie: SESSIONID=abc123 # Step 2: Login with same session POST /login HTTP/1.1 Cookie: SESSIONID=abc123 username=valid&password=valid # Step 3: Check if session changed # VULNERABLE if SESSIONID remains abc123 # SECURE if new session assigned after login

Attack scenario:

▼
bash
复制代码
# Attacker workflow: 1. Attacker visits site, gets session: SESSIONID=attacker_session 2. Attacker sends link to victim with fixed session: https://target.com/login?SESSIONID=attacker_session 3. Victim logs in with attacker's session 4. Attacker now has authenticated session

Phase 8: Session Timeout Testing

Verify session expiration policies:

▼
bash
复制代码
# Test idle timeout 1. Login and note session cookie 2. Wait without activity (15, 30, 60 minutes) 3. Attempt to use session 4. Check if session is still valid # Test absolute timeout 1. Login and continuously use session 2. Check if forced logout after set period (8 hours, 24 hours) # Test logout functionality 1. Login and note session 2. Click logout 3. Attempt to reuse old session cookie 4. Session should be invalidated server-side

Phase 9: Multi-Factor Authentication Testing

Assess MFA implementation security:

▼
bash
复制代码
# OTP brute force - 4-digit OTP = 10,000 combinations - 6-digit OTP = 1,000,000 combinations - Test rate limiting on OTP endpoint # OTP bypass techniques - Skip MFA step by direct URL access - Modify response to indicate MFA passed - Null/empty OTP submission - Previous valid OTP reuse # API Version Downgrade Attack (crAPI example) # If /api/v3/check-otp has rate limiting, try older versions: POST /api/v2/check-otp {"otp": "1234"} # Older API versions may lack security controls # Using Burp for OTP testing 1. Capture OTP verification request 2. Send to Intruder 3. Set OTP field as payload position 4. Use numbers payload (0000-9999) 5. Check for successful bypass

Test MFA enrollment:

▼
bash
复制代码
# Forced enrollment - Can MFA be skipped during setup? - Can backup codes be accessed without verification? # Recovery process - Can MFA be disabled via email alone? - Social engineering potential?

Phase 10: Password Reset Testing

Analyze password reset security:

▼
bash
复制代码
# Token security 1. Request password reset 2. Capture reset link 3. Analyze token: - Length and randomness - Expiration time - Single-use enforcement - Account binding # Token manipulation https://target.com/reset?token=abc123&user=victim # Try changing user parameter while using valid token # Host header injection POST /forgot-password HTTP/1.1 Host: attacker.com email=victim@email.com # Reset email may contain attacker's domain

Quick Reference

Common Vulnerability Types

VulnerabilityRiskTest Method
Weak passwordsHighPolicy testing, dictionary attack
No lockoutHighBrute force testing
Username enumerationMediumDifferential response analysis
Session fixationHighPre/post-login session comparison
Weak session tokensHighEntropy analysis
No session timeoutMediumLong-duration session testing
Insecure password resetHighToken analysis, workflow bypass
MFA bypassCriticalDirect access, response manipulation

Credential Testing Payloads

▼
bash
复制代码
# Default credentials admin:admin admin:password admin:123456 root:root test:test user:user # Common passwords 123456 password 12345678 qwerty abc123 password1 admin123 # Breached credential databases - Have I Been Pwned dataset - SecLists passwords - Custom targeted lists

Session Cookie Flags

FlagPurposeVulnerability if Missing
HttpOnlyPrevent JS accessXSS can steal session
SecureHTTPS onlySent over HTTP
SameSiteCSRF protectionCross-site requests allowed
PathURL scopeBroader exposure
DomainDomain scopeSubdomain access
ExpiresLifetimePersistent sessions

Rate Limiting Bypass Headers

▼
http
复制代码
X-Forwarded-For: 127.0.0.1 X-Real-IP: 127.0.0.1 X-Originating-IP: 127.0.0.1 X-Client-IP: 127.0.0.1 X-Remote-IP: 127.0.0.1 True-Client-IP: 127.0.0.1

Constraints and Limitations

Legal Requirements

  • Only test with explicit written authorization
  • Avoid testing with real breached credentials
  • Do not access actual user accounts
  • Document all testing activities

Technical Limitations

  • CAPTCHA may prevent automated testing
  • Rate limiting affects brute force timing
  • MFA significantly increases attack difficulty
  • Some vulnerabilities require victim interaction

Scope Considerations

  • Test accounts may behave differently than production
  • Some features may be disabled in test environments
  • Third-party authentication may be out of scope
  • Production testing requires extra caution

Examples

Example 1: Account Lockout Bypass

Scenario: Test if account lockout can be bypassed

▼
bash
复制代码
# Step 1: Identify lockout threshold # Try 5 wrong passwords for admin account # Result: "Account locked for 30 minutes" # Step 2: Test bypass via IP rotation # Use X-Forwarded-For header POST /login HTTP/1.1 X-Forwarded-For: 192.168.1.1 username=admin&password=attempt1 # Increment IP for each attempt X-Forwarded-For: 192.168.1.2 # Continue until successful or confirmed blocked # Step 3: Test bypass via case manipulation username=Admin (vs admin) username=ADMIN # Some systems treat these as different accounts

Example 2: JWT Token Attack

Scenario: Exploit weak JWT implementation

▼
bash
复制代码
# Step 1: Capture JWT token Authorization: Bearer eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJ1c2VyIjoidGVzdCJ9.signature # Step 2: Decode and analyze # Header: {"alg":"HS256","typ":"JWT"} # Payload: {"user":"test","role":"user"} # Step 3: Try "none" algorithm attack # Change header to: {"alg":"none","typ":"JWT"} # Remove signature eyJhbGciOiJub25lIiwidHlwIjoiSldUIn0.eyJ1c2VyIjoiYWRtaW4iLCJyb2xlIjoiYWRtaW4ifQ. # Step 4: Submit modified token Authorization: Bearer eyJhbGciOiJub25lIiwidHlwIjoiSldUIn0.eyJ1c2VyIjoiYWRtaW4ifQ.

Example 3: Password Reset Token Exploitation

Scenario: Test password reset functionality

▼
bash
复制代码
# Step 1: Request reset for test account POST /forgot-password email=test@example.com # Step 2: Capture reset link https://target.com/reset?token=a1b2c3d4e5f6 # Step 3: Test token properties # Reuse: Try using same token twice # Expiration: Wait 24+ hours and retry # Modification: Change characters in token # Step 4: Test for user parameter manipulation https://target.com/reset?token=a1b2c3d4e5f6&email=admin@example.com # Check if admin's password can be reset with test user's token

Troubleshooting

IssueSolutions
Brute force too slowIdentify rate limit scope; IP rotation; add delays; use targeted wordlists
Session analysis inconclusiveCollect 1000+ tokens; use statistical tools; check for timestamps; compare accounts
MFA cannot be bypassedDocument as secure; test backup/recovery mechanisms; check MFA fatigue; verify enrollment
Account lockout prevents testingRequest multiple test accounts; test threshold first; use slower timing
测试与安全

快捷安装

复制到终端去安装 Skill

npxskillsaddzebbern/claude-code-guide--skill"broken-authentication"
站长:程序员鱼皮 老鱼简历 商务合作 增值电信业务经营许可证
2026 鱼皮AI导航 | 沪ICP备19026706号-6
站长:程序员鱼皮 老鱼简历 商务合作 增值电信业务经营许可证
2026 鱼皮AI导航 | 沪ICP备19026706号-6
🔥热门工具
朱雀AI检测朱雀AI检测
朱雀AI检测助手朱雀AI检测助手
LovartLovart
老鱼简历老鱼简历
WritePass官网WritePass官网
面多多面多多
CursorCursor
星月写作星月写作
朱雀AI检测助手朱雀AI检测助手
零感AI零感AI
Skills 推荐
debug
debug 是一个系统化定位软件缺陷根因的技能,适用于用户报告 'fix'、'broken'、'error' 等问题或测试意外失败时。它通过可验证的假设、最小复现、因果链分析和回归测试,确保在修复前准确定位根本原因。
webapp-testing
提供本地 Web 应用的端到端测试能力,支持页面导航、元素交互、表单填写、动态等待、断言验证、截图捕获、浏览器日志收集及网络请求拦截,适用于前端功能验证与 UI 行为调试。
tdd-process
严格遵循测试驱动开发的红绿重构循环,强制执行先写测试、失败要有意义、实现最小化、验证全覆盖的全流程,确保每次代码变更都由可执行的测试用例驱动并经编译、检查与全量验证确认。
smoke-test
自动化创建 Mastra 项目并完成 Studio 全流程冒烟测试,涵盖项目初始化、环境配置、本地服务启动及 Chrome 浏览器中对 Agents、Tools、Workflows、Scorers 等核心模块的功能验证与截图记录。
property-based-testing
通过生成随机输入验证代码在各类边界条件下的行为一致性,适用于序列化、解析、归一化及纯函数等场景,能有效发现隐含缺陷并提升测试覆盖率,尤其适合需要高可靠性的算法与智能合约验证。