Skip to content

A Claude Code skill bundle for bug hunting and external red-team work - 82 skills, 15 slash commands, 681 disclosed-report patterns curated across 24 core vulnerability classes, plus enterprise identity + infrastructure attack matrices.

docs: add Pages site + searchable skill catalog + README quickstart

Sachin Sharmad6a00a2c2e2d
diff --git a/README.md b/README.md
index 8321110..db82b1f 100644
--- a/README.md
+++ b/README.md
@@ -25,6 +25,33 @@ All triggered automatically by topic — describe what you're testing in plain E
---
+## Quickstart
+
+```bash
+git clone https://github.com/elementalsouls/Claude-BugHunter.git
+cd Claude-BugHunter
+bash scripts/install.sh # copies skills + commands into ~/.claude/
+```
+
+That's it. Open Claude Code and describe what you're testing in plain English — the right skill loads automatically, no invocation by name:
+
+```text
+> Testing acme.com — an in-scope HackerOne target. Run recon and rank the surface.
+
+ ⟳ loading skills: web2-recon, offensive-osint, bb-methodology …
+ → subdomain enum (subfinder + crt.sh) … 47 hosts
+ → live hosts (httpx) … 12 · tech fingerprint … 6 distinct stacks
+ → ranked surface: api.acme.com (GraphQL, introspection ON) ← start here
+ auth.acme.com (OAuth, SSO) ← hunt-oauth
+ Next: want me to probe the GraphQL introspection + OAuth redirect_uri?
+```
+
+→ Full [Installation guide](INSTALL.md) · [Usage guide](USAGE.md) · [searchable skill catalog](docs/skills.md).
+
+> The block above is an illustrative transcript. To record a real demo of your own session: `asciinema rec demo.cast` → upload to [asciinema.org](https://asciinema.org) and drop the badge here.
+
+---
+
## Scope — what this bundle is for, and what it isn't
This bundle covers the **external attack surface** — anything reachable from the internet without first compromising an internal endpoint.
diff --git a/docs/_config.yml b/docs/_config.yml
new file mode 100644
index 0000000..a575dbf
--- /dev/null
+++ b/docs/_config.yml
@@ -0,0 +1,40 @@
+# GitHub Pages config for the claude-bughunter docs site.
+# Built from the /docs folder. Uses just-the-docs for built-in search.
+title: claude-bughunter
+description: >-
+ A Claude skill bundle that turns Claude Code into a senior bug-hunting
+ researcher and external red-team operator. 51+ skills, 681 disclosed-report
+ patterns, enterprise attack matrices, Burp MCP integration.
+remote_theme: just-the-docs/just-the-docs
+
+url: "https://elementalsouls.github.io"
+baseurl: "/Claude-BugHunter"
+
+# Search (just-the-docs built-in)
+search_enabled: true
+search:
+ heading_level: 2
+ previews: 3
+
+# Repo links in the nav footer
+aux_links:
+ "GitHub":
+ - "https://github.com/elementalsouls/Claude-BugHunter"
+ "Sponsor — Atlas Cloud":
+ - "https://www.atlascloud.ai/console/coding-plan"
+aux_links_new_tab: true
+
+color_scheme: dark
+heading_anchors: true
+
+# Don't try to render engineering/meta files as site pages.
+exclude:
+ - disclosed-reports/
+ - verification/
+ - automation/
+ - "*.py"
+ - ".DS_Store"
+
+plugins:
+ - jekyll-remote-theme
+ - jekyll-seo-tag
diff --git a/docs/index.md b/docs/index.md
new file mode 100644
index 0000000..7b2d9d0
--- /dev/null
+++ b/docs/index.md
@@ -0,0 +1,69 @@
+---
+title: Home
+nav_order: 1
+description: A Claude skill bundle for bug hunting and external red-team work.
+permalink: /
+---
+
+# claude-bughunter
+{: .fs-9 }
+
+A drop-in [Claude Code skill](https://docs.claude.com/en/docs/claude-code/skills)
+bundle that makes Claude behave like a senior bug-hunting researcher or red-team
+operator — it knows the techniques, the chain templates, the VRT mappings, the
+platform CVE chains, and the hygiene, and it stays in scope.
+{: .fs-6 .fw-300 }
+
+[Get started](#quickstart){: .btn .btn-primary .mr-2 }
+[Browse the skill catalog](./skills.html){: .btn }
+[View on GitHub](https://github.com/elementalsouls/Claude-BugHunter){: .btn }
+
+---
+
+## What you get
+
+- **51+ skills** across recon, 28 web-app vuln classes, enterprise platform attack,
+ red-team tradecraft, and reporting — all **auto-loading by topic**, no invocation
+ by name.
+- **681 disclosed-report patterns** curated from public HackerOne reports.
+- **Enterprise attack matrices** — M365/Entra, Okta, SharePoint, vCenter, SSL-VPN,
+ Android APK, supply-chain — with current 2024–2026 CVE chains.
+- **Reporting + validation** — 7-Question Gate, VRT mapping, evidence hygiene,
+ and a client-facing red-team deliverable format.
+- **Burp MCP integration** and an engagement-folder scaffold.
+
+## Quickstart
+
+```bash
+# Clone and install into ~/.claude/
+git clone https://github.com/elementalsouls/Claude-BugHunter.git
+cd Claude-BugHunter
+bash scripts/install.sh
+```
+
+Then open Claude Code and describe what you're testing in plain English —
+the relevant skill loads automatically:
+
+```
+> I'm testing acme.com, an in-scope HackerOne target. Start recon and
+ rank the attack surface.
+```
+
+See the full [Installation guide](https://github.com/elementalsouls/Claude-BugHunter/blob/main/INSTALL.md)
+and [Usage guide](https://github.com/elementalsouls/Claude-BugHunter/blob/main/USAGE.md).
+
+## Stay in scope
+
+This bundle is for assets you **own** or are **authorized to assess** (in-scope
+bug-bounty programs, signed-RoE pentests, CTFs, your own lab). It ships
+validation gates that auto-trigger on ambiguity. See the
+[Security policy](https://github.com/elementalsouls/Claude-BugHunter/blob/main/SECURITY.md).
+
+---
+
+## Sponsored by
+
+[Atlas Cloud](https://www.atlascloud.ai/console/coding-plan) — a full-modal AI
+inference platform: one API for video, image, and LLM models (300+ curated).
+Check out their [coding-plan promotion](https://www.atlascloud.ai/console/coding-plan)
+for budget-friendly API access.
diff --git a/docs/skills.md b/docs/skills.md
new file mode 100644
index 0000000..bf97b19
--- /dev/null
+++ b/docs/skills.md
@@ -0,0 +1,88 @@
+---
+title: Skill catalog
+nav_order: 2
+description: Searchable index of every skill in the bundle.
+---
+
+# Skill catalog
+
+All **51 skills** in the bundle, grouped by domain. Each auto-loads when your prompt matches its trigger keywords — no need to invoke by name. Use your browser's find (⌘/Ctrl-F) or the docs search box.
+
+> Generated by `scripts/gen_skill_catalog.py` — do not edit by hand.
+
+## Hunt — web app vuln classes (28)
+
+| Skill | What it does | Reports |
+|---|---|---|
+| `hunt-api-misconfig` | Hunt API security misconfiguration — mass assignment, JWT attacks, prototype pollution, CORS, HTTP verb tampering. | — |
+| `hunt-aspnet` | Hunt ASP.NET-specific surface — ViewState deserialization (signed-only vs encrypted), machineKey recovery, dual-parser MAC-bypass anti-pattern, request-validator bypass, trace.axd/elmah.axd disclosure, load-balanced ViewState cross-node… | 1 |
+| `hunt-ato` | Hunt account takeover taxonomy — 9 distinct paths to ATO, plus chains. | — |
+| `hunt-auth-bypass` | Hunting skill for auth bypass vulnerabilities. | 12 |
+| `hunt-business-logic` | Hunting skill for business logic vulnerabilities. | 12 |
+| `hunt-cache-poison` | Hunting skill for cache poison vulnerabilities. | 10 |
+| `hunt-cloud-misconfig` | Hunt cloud / infrastructure misconfigurations. | — |
+| `hunt-csrf` | Hunting skill for csrf vulnerabilities. | 15 |
+| `hunt-dispatch` | Skill-set loader for /hunt orchestrator. | — |
+| `hunt-file-upload` | Hunt file upload bugs — RCE via webshell, XSS via SVG/HTML, SSRF via XXE in DOCX, path traversal via filename. | — |
+| `hunt-graphql` | Hunting skill for graphql vulnerabilities. | 12 |
+| `hunt-http-smuggling` | Hunt HTTP request smuggling (CL.TE, TE.CL, H2.CL, H2.TE). | — |
+| `hunt-idor` | Hunting skill for idor vulnerabilities. | 26 |
+| `hunt-llm-ai` | Hunt LLM/AI feature bugs — prompt injection, indirect injection, exfiltration via tool-use, ASCII smuggling, agentic AI security framework (ASI01-ASI10). | — |
+| `hunt-mfa-bypass` | Hunt MFA / 2FA bypass — 7 distinct patterns. | — |
+| `hunt-misc` | Hunting skill for misc vulnerabilities. | 225 |
+| `hunt-ntlm-info` | Hunt NTLM/Negotiate information disclosure on internet-reachable IIS/SharePoint/Exchange. | 1 |
+| `hunt-oauth` | Hunting skill for oauth vulnerabilities. | 19 |
+| `hunt-race-condition` | Hunting skill for race condition vulnerabilities. | 12 |
+| `hunt-rce` | Hunting skill for rce vulnerabilities. | 67 |
+| `hunt-saml` | Hunt SAML / SSO attacks. | — |
+| `hunt-sharepoint` | Hunt Microsoft SharePoint Server (2013/2016/2019/Subscription Edition) on-prem farms — anonymous endpoint enumeration, version disclosure, legacy SOAP login bypass (Authentication.asmx), ToolShell precondition chain (CVE-2025-53770),… | 1 |
+| `hunt-sqli` | Hunting skill for sqli vulnerabilities. | 12 |
+| `hunt-ssrf` | Hunting skill for ssrf vulnerabilities. | 15 |
+| `hunt-ssti` | Hunt server-side template injection (SSTI) across Jinja2 (Flask/Django), Twig (Symfony), Freemarker (Java), ERB (Rails), Spring, Velocity, Mako, Thymeleaf, Smarty. | — |
+| `hunt-subdomain` | Hunting skill for subdomain vulnerabilities. | 15 |
+| `hunt-xss` | Hunting skill for xss vulnerabilities. | 174 |
+| `hunt-xxe` | Hunting skill for xxe vulnerabilities. | 10 |
+
+## Enterprise platform attack (9)
+
+| Skill | What it does | Reports |
+|---|---|---|
+| `apk-redteam-pipeline` | End-to-end Android APK red-team pipeline — automated APK acquisition (Play Store + apkpure + apkmirror fallback), jadx decompilation, secret/URL/JWT/Firebase grep, pinned-cert extraction, exported-component enumeration, Frida runtime… | 1 |
+| `cloud-iam-deep` | Cloud IAM red-team attack chain across AWS, Azure, GCP — focused on EXTERNAL exploitation paths and post-credential-discovery privilege analysis. | 6 |
+| `enterprise-vpn-attack` | External SSL VPN / remote-access appliance attack matrix — Cisco ASA/AnyConnect, Fortinet FortiGate/FortiOS, Citrix NetScaler/ADC, Palo Alto GlobalProtect, Pulse Secure / Ivanti Connect Secure, SonicWall, F5 Big-IP. | 1 |
+| `m365-entra-attack` | Microsoft 365 / Entra ID red-team attack chain — current 2026 reality. | 1 |
+| `meme-coin-audit` | Meme coin and token security audit — rug pull detection (honeypot, hidden mint, fee manipulation, LP lock bypass), Solana SPL token analysis (freeze authority, mint authority, metadata mutability), Token-2022 extension risks (transfer… | — |
+| `okta-attack` | Okta-as-IdP red-team attack chain — tenant discovery, user enumeration (multiple vectors), authentication flow analysis (factors enumeration, push-notification fatigue, SMS bypass), password spray with lockout discipline, Okta-specific… | 8 |
+| `supply-chain-attack-recon` | External recon for software supply-chain attack surface — package-namespace squatting candidates, dependency-confusion vulnerabilities, GitHub Actions injection openings, container image registry exposure, SBOM mining,… | 12 |
+| `vmware-vcenter-attack` | VMware vSphere / vCenter Server external attack matrix — version fingerprinting, the high-impact CVE chain (CVE-2021-21972 vRealize unauth file upload, CVE-2021-21985 vSAN plugin RCE, CVE-2022-22954 Workspace ONE SSTI, CVE-2023-20887 Aria… | 10 |
+| `web3-audit` | Smart contract security audit — 10 DeFi bug classes (accounting desync, access control, incomplete path, off-by-one, oracle, ERC4626, reentrancy, flash loan, signature replay, proxy), pre-dive kill signals (TVL < $500K etc), Foundry PoC… | — |
+
+## Recon & OSINT (4)
+
+| Skill | What it does | Reports |
+|---|---|---|
+| `offensive-osint` | Operational arsenal for authorized external red-team and bug-bounty recon. | — |
+| `osint-methodology` | Comprehensive OSINT methodology for external red-team operations and authorized attack-surface assessments. | — |
+| `security-arsenal` | Security payloads, bypass tables, wordlists, gf pattern names, always-rejected bug list, and conditionally-valid-with-chain table. | — |
+| `web2-recon` | Web2 recon pipeline — subdomain enumeration (subfinder, Chaos API, assetfinder), live host discovery (dnsx, httpx), URL crawling (katana, waybackurls, gau), directory fuzzing (ffuf), JS analysis (LinkFinder, SecretFinder), continuous… | — |
+
+## Methodology & mindset (4)
+
+| Skill | What it does | Reports |
+|---|---|---|
+| `bb-local-toolkit` | Complete bug bounty workflow — recon (subdomain enumeration, asset discovery, fingerprinting, HackerOne scope, source code audit), pre-hunt learning (disclosed reports, tech stack research, mind maps, threat modeling), vulnerability… | — |
+| `bb-methodology` | Use at the START of any bug bounty hunting session, when switching targets, or when feeling lost about what to do next. | — |
+| `bug-bounty` | Complete bug bounty workflow — recon (subdomain enumeration, asset discovery, fingerprinting, HackerOne scope, source code audit), pre-hunt learning (disclosed reports, tech stack research, mind maps, threat modeling), vulnerability… | — |
+| `redteam-mindset` | Red-team operator discipline — the mindset corrections that separate offensive testing from defensive WAPT. | 1 |
+
+## Reporting & validation (6)
+
+| Skill | What it does | Reports |
+|---|---|---|
+| `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… | — |
+| `evidence-hygiene` | Evidence-capture and PoC-redaction discipline for bug-bounty submissions: cookie redaction protocol (which fields to mask, Preview annotation / Burp panel hiding / DevTools workflow), PII black-bar discipline (what to mask in other-user… | — |
+| `mid-engagement-ir-detection` | Methodology for detecting client SOC patches, attacker activity, and security-state changes that occur DURING a red-team engagement — and converting those observations into deliverable findings. | 1 |
+| `redteam-report-template` | Client-facing red-team deliverable format — codifies the Subject / Observations / Description / Impact / Recommendation / PoC structure used for external red-team engagements (not bug-bounty platform reports). | 1 |
+| `report-writing` | Bug bounty report writing for H1/Bugcrowd/Intigriti/Immunefi — report templates, human tone guidelines, impact-first writing, CVSS 3.1 scoring, title formula, impact statement formula, severity decision guide, downgrade counters,… | — |
+| `triage-validation` | Finding validation before writing any report — 7-Question Gate (all 7 questions), 4 pre-submission gates, always-rejected list, conditionally valid with chain table, CVSS 3.1 quick reference, severity decision guide, report title formula,… | — |
+
diff --git a/scripts/gen_skill_catalog.py b/scripts/gen_skill_catalog.py
new file mode 100644
index 0000000..d5f09ca
--- /dev/null
+++ b/scripts/gen_skill_catalog.py
@@ -0,0 +1,117 @@
+#!/usr/bin/env python3
+"""
+gen_skill_catalog.py — generate docs/skills.md from every skill's frontmatter.
+
+Keeps the public skill catalog in sync with what's actually on disk. Run after
+adding/editing skills:
+
+ python3 scripts/gen_skill_catalog.py
+
+Reads name/description/report_count from each skills/<name>/SKILL.md and writes a
+searchable, grouped catalog page (Jekyll front matter included for the docs site).
+Stdlib only.
+"""
+import os
+import re
+
+REPO = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+SKILLS_DIR = os.path.join(REPO, "skills")
+OUT = os.path.join(REPO, "docs", "skills.md")
+
+# Grouping by name prefix / known membership. Order defines section order.
+GROUPS = [
+ ("Hunt — web app vuln classes", lambda n: n.startswith("hunt-")),
+ ("Enterprise platform attack", lambda n: n in {
+ "m365-entra-attack", "okta-attack", "cloud-iam-deep", "vmware-vcenter-attack",
+ "enterprise-vpn-attack", "apk-redteam-pipeline", "supply-chain-attack-recon",
+ "meme-coin-audit", "web3-audit"}),
+ ("Recon & OSINT", lambda n: "osint" in n or "recon" in n or n == "security-arsenal"),
+ ("Methodology & mindset", lambda n: n in {
+ "bb-methodology", "bug-bounty", "bb-local-toolkit", "redteam-mindset"}),
+ ("Reporting & validation", lambda n: n in {
+ "report-writing", "triage-validation", "bugcrowd-reporting", "evidence-hygiene",
+ "redteam-report-template", "mid-engagement-ir-detection"}),
+]
+
+
+def parse_frontmatter(path):
+ name = desc = ""
+ report_count = None
+ with open(path, encoding="utf-8") as fh:
+ raw = fh.read()
+ if not raw.startswith("---"):
+ return None
+ lines = raw.split("\n")
+ for i in range(1, len(lines)):
+ if lines[i].strip() == "---":
+ break
+ m = re.match(r"^(name|description|report_count):\s*(.*)$", lines[i])
+ if m:
+ k, v = m.group(1), m.group(2).strip()
+ if len(v) >= 2 and v[0] == v[-1] and v[0] in "\"'":
+ v = v[1:-1].strip()
+ if k == "name":
+ name = v
+ elif k == "description":
+ desc = v
+ elif k == "report_count":
+ report_count = v
+ return {"name": name, "description": desc, "report_count": report_count}
+
+
+def first_sentence(text, limit=240):
+ text = text.strip()
+ cut = re.split(r"(?<=[.。])\s", text, maxsplit=1)[0]
+ if len(cut) > limit:
+ cut = cut[:limit].rsplit(" ", 1)[0] + "…"
+ return cut
+
+
+def main():
+ skills = []
+ for d in sorted(os.listdir(SKILLS_DIR)):
+ sp = os.path.join(SKILLS_DIR, d, "SKILL.md")
+ if os.path.isfile(sp):
+ fm = parse_frontmatter(sp)
+ if fm and fm["name"]:
+ skills.append(fm)
+
+ assigned = set()
+ sections = []
+ for title, pred in GROUPS:
+ members = [s for s in skills if s["name"] not in assigned and pred(s["name"])]
+ for s in members:
+ assigned.add(s["name"])
+ if members:
+ sections.append((title, members))
+ leftover = [s for s in skills if s["name"] not in assigned]
+ if leftover:
+ sections.append(("Other", leftover))
+
+ total = len(skills)
+ with open(OUT, "w", encoding="utf-8") as out:
+ out.write("---\n")
+ out.write("title: Skill catalog\n")
+ out.write("nav_order: 2\n")
+ out.write("description: Searchable index of every skill in the bundle.\n")
+ out.write("---\n\n")
+ out.write("# Skill catalog\n\n")
+ out.write(f"All **{total} skills** in the bundle, grouped by domain. "
+ "Each auto-loads when your prompt matches its trigger keywords — "
+ "no need to invoke by name. Use your browser's find (⌘/Ctrl-F) "
+ "or the docs search box.\n\n")
+ out.write("> Generated by `scripts/gen_skill_catalog.py` — do not edit by hand.\n\n")
+ for title, members in sections:
+ out.write(f"## {title} ({len(members)})\n\n")
+ out.write("| Skill | What it does | Reports |\n")
+ out.write("|---|---|---|\n")
+ for s in sorted(members, key=lambda x: x["name"]):
+ rc = s["report_count"] or "—"
+ desc = first_sentence(s["description"]).replace("|", "\\|")
+ out.write(f"| `{s['name']}` | {desc} | {rc} |\n")
+ out.write("\n")
+ print(f"Wrote {OUT} — {total} skills across {len(sections)} sections.")
+
+
+if __name__ == "__main__":
+ main()