authentication · transilienceai — Claude Code skill: tests and installation
This skill checks login flows, tokens, 2FA, CAPTCHA, and bot detection. Use it to examine auth bypasses and weaknesses in authentication controls.
MIT 212 installs ★ 632 updated 2026-07-29
npx skills add transilienceai/communitytools --skill authentication -a claude-codeWhat authentication does
The skill examines login forms, token handling, 2FA, CAPTCHA, and bot detection. Its checks cover auth bypass, JWT and OAuth attacks, password controls, ADFS/SAML, code reuse, and parameter tampering. The workflow records screenshots, network logs, tokens, and PoC scripts as evidence.
It includes tools/password_generator.py for creating passwords and tools/credential_manager.py for storing credentials. Reference files cover JWT, OAuth, ADFS, password attacks, 2FA, CAPTCHA, and bot detection. Playwright MCP is needed for the browser-based workflow, which uses human-like interaction patterns.
The skill is available for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode. The example utilities require Python.
What it helps with
- test authentication bypass paths
- inspect JWT and OAuth handling
- check whether 2FA codes can be reused
- probe password controls against brute force and stuffing
- capture evidence for a security finding
Example prompts for the agent
- Review the project’s login forms, tokens, 2FA, and CAPTCHA, then map possible bypass tests.
- Test the JWT flow for claim tampering, algorithm confusion, and forged tokens.
- Check the login protection against brute force, credential stuffing, and reused 2FA codes.
How to install authentication
1Skills CLI (Vercel)
npx skills add transilienceai/communitytools --skill authentication -a claude-code2Manually: put the files in place
~/.claude/skills/authentication/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/authentication/
1Skills CLI (Vercel)
npx skills add transilienceai/communitytools --skill authentication -a codex2Manually: put the files in place
.agents/skills/authentication/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add transilienceai/communitytools --skill authentication -a cursor2Manually: put the files in place
.cursor/skills/authentication/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install transilienceai/communitytools skills/authentication2Manually: put the files in place
.github/skills/authentication/SKILL.md1Skills CLI (Vercel)
npx skills add transilienceai/communitytools --skill authentication -a gemini-cli2Platform CLI
gemini skills install https://github.com/transilienceai/communitytools --path skills/authenticationManually: put the files in place
.devin/skills/authentication/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add transilienceai/communitytools --skill authentication -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about authentication
How do I install authentication in Claude Code?
Run npx skills add transilienceai/communitytools --skill authentication -a claude-code. The skill file will be placed at ~/.claude/skills/authentication/SKILL.md.
What does authentication do?
It examines authentication controls covering login bypass, JWT, OAuth, passwords, 2FA, CAPTCHA, and bot detection. It also lays out evidence collection with screenshots, network logs, tokens, and PoC scripts.
What is needed for browser checks with authentication?
The workflow uses Playwright MCP for browser scenarios. The included utilities run with Python.
Source text
SKILL.md · MIT
--- name: authentication description: Authentication security testing - auth bypass, JWT attacks, OAuth flaws, password attacks, 2FA bypass, CAPTCHA bypass, and bot detection evasion. --- # Authentication Test authentication mechanisms including login security, token handling, 2FA, CAPTCHA, and bot detection. ## Techniques | Type | Key Vectors | |------|-------------| | **Auth Bypass** | Default credentials, logic flaws, response manipulation | | **ADFS/SAML** | Golden SAML, token signing cert theft, assertion manipulation, SAML wrapping | | **JWT** | Algorithm confusion, key injection, claim tampering, token forging | | **OAuth** | Redirect manipulation, CSRF, token leakage, scope abuse | | **Password** | Brute force, credential stuffing, password policy bypass | | **2FA Bypass** | Response manipulation, direct endpoint access, code reuse, race conditions | | **CAPTCHA Bypass** | Missing server validation, token reuse, OCR, parameter manipulation | | **Bot Detection** | Behavioral biometrics simulation, fingerprint randomization, stealth mode | ## Tools **PasswordGenerator** (`tools/password_generator.py`): ```python from tools.password_generator import generate_password password = generate_password(hint_text="8-16 chars, uppercase, numbers") ``` **CredentialManager** (`tools/credential_manager.py`): ```python from tools.credential_manager import CredentialManager mgr = CredentialManager() mgr.store_credential(target="example.com", username="test", password="pass") ``` ## Workflow 1. Analyze auth implementation (forms, tokens, 2FA, CAPTCHA) 2. Test bypass vectors per technique type 3. Use Playwright MCP with human-like behavior (typing 80-200ms, random pauses) 4. Capture evidence (screenshots, network logs, tokens) 5. Document findings with PoC scripts ## Reference - `reference/authentication*.md` - Auth bypass techniques, payloads, and resources - `reference/jwt*.md` - JWT attack techniques and cheat sheets - `reference/oauth*.md` - OAuth vulnerability testing - `reference/scenarios/password-attacks/*.md` - Password attack vectors (spray, stuffing, cracking, PtH) - `reference/adfs-exploitation.md` - ADFS, Golden SAML, federation attacks - `reference/scenarios/2fa/*.md` - 2FA bypass methods - `reference/CAPTCHA_BYPASS.md` - 11 CAPTCHA bypass techniques - `reference/BOT_DETECTION.md` - Bot detection evasion strategies - `reference/PASSWORD_CREDENTIAL_MANAGEMENT.md` - Tool usage guide
© transilienceai · MIT · transilienceai/communitytools
Similar skills
All skills for Backend and APIs →authentication by other authors comes first.