Skip to main content
rule CX Codex

pentest-agents-chain-table — Claude Code rule: setup

pentest-agents-chain-table is a Claude Code rule that directs security audit agents to chain verified vulnerabilities into exploit paths.

no license ★ 1,298 updated 2026-06-12

Install into GitHub Copilot · Manually: put the files in place All methods and platforms ↓
.github/instructions/pentest-agents-chain-table.instructions.md
Open on GitHub

What pentest-agents-chain-table does

The rule outlines the Chain Walk workflow for security testing agents. Once an agent verifies an initial bug, it identifies the resulting capability and consults an internal mapping table to test subsequent vectors. Every hop enforces a strict 20-minute cap and tolerates at most three consecutive candidate failures at that depth.

Included tables map findings like text injection, open redirects, SSRF, and cross-origin misconfigurations to deeper outcomes. An agent cannot simply mark standalone issues complete: it must validate specific feeder anchors with exact HTTP traffic pairs until reaching a defined terminal state.

What it helps with

  • chain low-severity findings into documented privilege escalation paths
  • systematize secondary checks for open redirects and CORS flaws
  • enforce timeouts and failure limits during vulnerability chaining
  • verify multi-step security flows using exact request and response pairs

Example prompts for the agent

  • Evaluate potential escalation links from an initial SSRF finding
  • Run the chain walk algorithm on the confirmed redirect bug
  • Inspect cross-origin misconfigurations against the feeder anchors list

How to install pentest-agents-chain-table

Manually: put the files in place

.github/instructions/pentest-agents-chain-table.instructions.md

The applyTo field sets which files it applies to

Step by step, with commands for each platform: AGENTS.md vs CLAUDE.md: what they are and which one to use

Questions about pentest-agents-chain-table

How to install pentest-agents-chain-table in Claude Code?

Place the file at .claude/rules/pentest-agents-chain-table.md inside your project directory.

What does pentest-agents-chain-table do?

It guides AI agents through mapping verified security primitives into complete escalation chains.

What failure limits does the chaining algorithm enforce?

The rule limits each hop to a 20-minute testing window and permits at most three candidate failures per depth.

Similar IDE rules

All IDE rules for Security →

From the same set43

The whole set →
sast-devils-advocate sast-devils-advocate is a Claude Code subagent that challenges SAST findings by looking for reasons a reported flaw cannot be exploited. Run it with /sast. CX Codex +1 ★ 1,298repo stars pentest-agents-payloads-7 The pentest-agents-payloads-7 rule for Claude Code provides test scenarios for SSRF, parameter injection, prototype pollution, and OAuth flaws during web security audits. CX Codex +1 ★ 1,298repo stars pentest-agents-payloads-1 pentest-agents-payloads-1 is a Claude Code rule that loads an XSS payload reference for pentesting, from basic vectors to WAF bypass via stacked encoding. CX Codex +1 ★ 1,298repo stars pentest-agents-payloads-4 pentest-agents-payloads-4 is a Claude Code rule with examples for reviewing web vulnerabilities, from JWT and deserialization to GraphQL and OAuth. It supports application security assessments. CX Codex +1 ★ 1,298repo stars report-writer report-writer turns vulnerability findings into bug bounty submissions, penetration test reports, or technical write-ups. Use it when findings need clear evidence, impact, and remediation. CX Codex +1 ★ 1,298repo stars sast-danger-mapper sast-danger-mapper catalogs hazardous source code operations using pattern matching without speculating on exploitability. CX Codex +1 ★ 1,298repo stars sast-danger-mapper sast-danger-mapper — a subagent that finds dangerous operations in source files: memory handling, type casts, arithmetic at trust boundaries, resource deallocation. CX Codex +1 ★ 1,298repo stars report-writer The report-writer subagent for Claude Code compiles vulnerability findings into reports for pentests, bounty submissions, and technical writeups. CX Codex +1 ★ 1,298repo stars

Project sponsors

Companies that keep this analytics open