vuln-chain-composer

vuln-chain-composer is a skill for Claude Code, Codex from Orizon-eu/claude-code-pentest. It costs 98 tokens per session (1,735 once invoked), scanned A, original, MIT.

A tool for combining separate security findings into multi-step attack scenarios. It connects weaknesses across systems and shows how they may produce a larger real-world impact.

In plain words
What is it for?
Correlating findings, building attack paths, creating end-to-end proof-of-concept scripts, and preparing bug-bounty reports for authorized targets.
Why use it?
A vulnerability that looks minor alone can become serious when combined with another; this helps testers understand those relationships.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Correlating findings, building attack paths, creating end-to-end proof-of-concept scripts, and preparing bug-bounty reports for authorized targets.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/orizon-eu/claude-code-pentest/vuln-chain-composer
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.

Any agent
npx skills add Orizon-eu/claude-code-pentest --skill vuln-chain-composer
Clone the repo
git clone --depth 1 https://github.com/Orizon-eu/claude-code-pentest

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 vuln-chain-composer

README.md
[![agentmods](https://agentmods.dev/badge/skills/orizon-eu/claude-code-pentest/vuln-chain-composer/github.svg)](https://agentmods.dev/skills/orizon-eu/claude-code-pentest/vuln-chain-composer)
Your own site
<a href="https://agentmods.dev/skills/orizon-eu/claude-code-pentest/vuln-chain-composer"><img src="https://agentmods.dev/badge/skills/orizon-eu/claude-code-pentest/vuln-chain-composer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for vuln-chain-composer

Your own site · 80×15
<a href="https://agentmods.dev/skills/orizon-eu/claude-code-pentest/vuln-chain-composer"><img src="https://agentmods.dev/badge/skills/orizon-eu/claude-code-pentest/vuln-chain-composer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,735 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00098 $0.01735
Opus 5 $0.00049 $0.00868
Sonnet 5 $0.00020 $0.00347
Haiku 4.5 $0.00010 $0.00173

Measured 10d ago against content hash 469cb686e608, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

vuln-chain-composer 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 10d ago.

The scan reads SKILL.md. This mod also ships 6 executable files (scripts/build_chains.py, scripts/calculate_impact.py, scripts/correlate.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

3. **curl command sequence** for manual reproduction
vuln-chain-composer/SKILL.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vuln Chain Composer

The strategic brain. Correlates individual vulnerabilities into devastating multi-step exploit chains.

Important

CRITICAL: This skill produces offensive security analysis. Only use with explicit authorization on the target systems.

Instructions

Step 1: Import Findings

Accept vulnerability data from:

  1. JSON output from webapp-exploit-hunter, api-breaker, cloud-pivot-finder
  2. Manual finding descriptions from the user
  3. Attack tree data from attack-path-architect
  4. Mixed sources - consolidate everything
python scripts/import_findings.py --input {findings_dir_or_files}

Normalize all findings to a common format:

  • Vulnerability type (SQLi, XSS, SSRF, IDOR, etc.)
  • Location (domain, URL, parameter)
  • Severity (standalone)
  • PoC (if available)
  • Prerequisites (authentication level, specific conditions)

Step 2: Cross-Domain Correlation

python scripts/correlate.py --findings {normalized_findings}

Analyze relationships between findings:

Same-Origin Chains:

  • XSS on subdomain A + sensitive cookies scoped to parent domain = session hijack on all subdomains
  • SSRF on subdomain B + internal API access = data exfiltration via internal endpoints
  • Open redirect on auth endpoint + OAuth callback = token theft

Trust-Based Chains:

  • Subdomain takeover + same cookie scope = full session hijack
  • CI/CD access + deployment pipeline = production RCE
  • Cloud metadata via SSRF + IAM overprivilege = full cloud compromise

Credential-Based Chains:

  • SQL injection + password hashes = credential cracking + account takeover
  • .env file exposure + database credentials = direct data access
  • IDOR on user profile + email exposure = targeted phishing + account takeover

Escalation Chains:

  • Low-privilege IDOR + mass assignment = privilege escalation to admin
  • Self-XSS + CSRF = weaponized stored XSS affecting other users
  • Rate limit bypass + brute-force + OTP bypass = authentication bypass

Step 3: Chain Construction

Read the full file on GitHub · 222 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 222 lines · 98 tokens per session scan A 469cb686e608

Subscribe to this mod's changes

vuln-chain-composer is a skill published in the GitHub repository Orizon-eu/claude-code-pentest (25 stars, last pushed 6mo ago), licensed MIT. It adds 98 tokens to every session and 1,735 once invoked, about $0.0005 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

forensics-kit

Digital forensics and incident response toolbox. Load when the operator asks about a pcap, a binary, a memory dump, a suspicious file, malware triage, IOC hunting, or post-incident analysis. Covers network (tshark), binaries (radare2, strings, binwalk, file, exiftool), memory (volatility), and pattern matching (YARA).…

FrancescoStabile/numasec · 101 tokens

passive-osint

Passive reconnaissance against a target without sending traffic that could alert it. Load when the engagement starts, when you only know a domain/email/username, when scope is unclear, or when you need historical surface area. Covers subdomain enumeration (crt.sh, subfinder), historical archives (wayback), DNS posture…

FrancescoStabile/numasec · 99 tokens

mobile-pentest

Mobile app pentest for bug bounty (Android APK + iOS IPA) — runtime-first workflow: install app, proxy through Burp/mitmproxy, drive the UI, capture packets, then test the API exactly like a web target; escalate to decompile (apktool/jadx) and Frida/objection only when traffic is SSL-pinned, encrypted, or absent.…

Awarexone/Agentic-Bug-Hunter · 205 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

hunt-api-misconfig

Hunt API security misconfiguration — mass assignment, prototype pollution, HTTP verb tampering. Mass assignment: send {isadmin:true, role:admin, verified:true} on profile/account/reset endpoints — server blindly applies. JWT signature/crypto forging (alg:none, key confusion, kid/jku) is owned by hunt-jwt-crypto; this…

elementalsouls/Claude-BugHunter · 207 tokens

hunt-ato

Hunt account takeover taxonomy — 9 distinct paths to ATO, plus chains. Paths: (1) password reset flaws (host-header injection redirects token, predictable/numeric token, Referer leak, no-expiry/reuse), (2) email change without re-auth, (3) OAuth account-link CSRF, (4) MFA bypass (per hunt-mfa-bypass), (5) session…

elementalsouls/Claude-BugHunter · 241 tokens