auth-bypass

auth-bypass is a skill for Claude Code, Codex from ShulkwiSEC/bb-huge. It costs 80 tokens per session (1,728 once invoked), scanned A, original, MIT.

A security-testing tool for demonstrating ways poorly designed websites can be tricked into accepting an unauthorised user or request.

In plain words
What is it for?
Testing web applications for authentication and session-management flaws, including forced browsing, parameter tampering, SQL injection, insecure deserialization, and HTTP credential exposure.
Why use it?
It helps identify authentication weaknesses such as exposed protected pages, changeable role flags, predictable session cookies, unsafe login queries, and insecure credential transport.

Skill for Claude CodeCodex

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 skills/shulkwisec/bb-huge/auth-bypass
Any agent
npx skills add ShulkwiSEC/bb-huge --skill auth-bypass
Clone the repo
git clone --depth 1 https://github.com/ShulkwiSEC/bb-huge

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for auth-bypass

README.md
[![agentmods](https://agentmods.dev/badge/skills/shulkwisec/bb-huge/auth-bypass.svg)](https://agentmods.dev/skills/shulkwisec/bb-huge/auth-bypass)
Your own site
<a href="https://agentmods.dev/skills/shulkwisec/bb-huge/auth-bypass"><img src="https://agentmods.dev/badge/skills/shulkwisec/bb-huge/auth-bypass.svg" alt="Measured on agentmods" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,728 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 5.1 $0.00080 $0.01728
Opus 5 $0.00040 $0.00864
Sonnet 5 $0.00016 $0.00346
Haiku 4.5 $0.00008 $0.00173

Measured 5d ago against content hash d5db48b6a155, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

auth-bypass scanned grade A with 1 finding 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 5d ago.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s http://TARGET/admin/dashboard -o /dev/null -w "%{http_code}"
skills/curated/auth-bypass/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Authentication Bypass

What Is Broken and Why

Authentication logic applied only at the login page leaves all downstream pages unprotected. Applications relying on client-supplied flags (authenticated, role, admin) to gate access allow trivial bypass by modifying those values. Predictable session tokens enable forging. Insecure deserialization in cookie handling allows boolean type juggling to short-circuit credential verification. Credentials transmitted over HTTP expose them to passive interception. Browser caching of authenticated responses allows offline credential harvesting from shared machines.

Key Signals

  • Login redirect but direct URL access to /dashboard, /admin, /profile returns 200
  • Parameters like authenticated=, isAdmin=, role=, debug=, fromtrustIP= in GET/POST/cookies
  • Session cookies with sequential, time-based, or partially-static values
  • Login form accepting ' OR '1'='1 or similar SQL payloads
  • Application serializes auth state into cookies (a:2:{s:11:"autologinid";...})
  • Login or registration form submitting over http:// instead of https://
  • Absence of Secure flag on session cookies
  • No Cache-Control: no-store on pages containing sensitive data
  • Set-Cookie not issuing new token after successful authentication (session fixation overlap)

Methodology

  1. Map all authenticated endpoints: Spider application; note every URL requiring login.
  2. Forced browsing: Without authenticating, request each protected URL directly. Record any that return 200 or partial content.
  3. Parameter tampering: Intercept login and post-login requests; add or modify boolean parameters (authenticated=yes, admin=true, debug=true, fromtrustIP=true).
  4. Cookie manipulation: Decode cookies (base64, URL, serialization); identify role/auth fields; modify and re-submit.
  5. Session prediction: Collect 50+ session tokens under identical conditions; analyze for patterns (incrementing integers, timestamp encoding, partial static prefix).
  6. SQL injection on login: Attempt classic payloads in username/password fields.
  7. Deserialization probe: If PHP serialized format detected in cookie, craft boolean bypass.
  8. Transport test: Replace https:// with http:// for login, registration, and password flows; observe if credentials submit over plain HTTP.
  9. Cache test: Log in, log out, press Back; reload authenticated pages; check local cache files.

Read the full file on GitHub · 145 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. 5d ago First seen · 145 lines · 80 tokens per session scan A d5db48b6a155

Subscribe to this mod's changes

auth-bypass is a skill published in the GitHub repository ShulkwiSEC/bb-huge (22 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 1,728 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

skill-context-detection

Auto-detect work context (Dev vs Knowledge) — use to tailor workflows based on current task type.

nyldn/claude-octopus · 25 tokens

skill-copilot-provider

GitHub Copilot CLI as optional zero-cost provider via copilot -p programmatic mode.

nyldn/claude-octopus · 24 tokens

bugcrowd-reporting

Bugcrowd-specific reporting tactics complementing report-writing: VRT category search-and-fallback strategy when no exact match exists, manual severity override when VRT defaults underrate impact, severity-request paragraph as first body section, OOS-clause rebuttal templates (rate limiting on auth-flow endpoints…

elementalsouls/Claude-BugHunter · 171 tokens

race

Race condition / TOCTOU playbook — limit overrun (one-time codes used twice, gift cards spent twice), single-packet attack (last-byte sync) to force parallel processing, and state-confusion races (file upload + read, order before payment). Use when timing-sensitive logic could be abused — one-time codes, coupons/gift…

PentesterFlow/agent · 82 tokens

skill-security-framing

URL validation and content sanitization for untrusted sources — use when handling external input safely.

nyldn/claude-octopus · 22 tokens

my-skill

One line on what this playbook does, then a "Use when ..." clause so the agent knows when to load it (e.g. "Use when the target exposes X / you see Y in requests"). Max 1024 chars. This description is the ONLY thing the model sees until it loads the skill — make the trigger conditions explicit, since there is no…

PentesterFlow/agent · 84 tokens