Skip to main content
rule CX Codex

pentest-agents-techniques — Claude Code rule: what it does

The pentest-agents-techniques rule guides agents through checks for authorization flaws and data leaks in web apps. Use it when testing systems you’re authorized to assess.

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-techniques.instructions.md
Open on GitHub

What pentest-agents-techniques does

The rule covers checks involving GraphQL and Django REST Framework, OAuth and PKCE, source maps, gRPC proxies, and differences in error responses. It describes signals that may point to an authorization bypass, code leakage, or exposed API schema.

Its techniques include comparing responses with and without credentials, inspecting GraphQL error hints, and checking for accessible source maps. The rule applies across project files (**). Some checks involve mutations or request enumeration, so keep them within an authorized test environment.

What it helps with

  • check whether GraphQL operations enforce authorization
  • look for OAuth code exposure to analytics
  • identify accessible source maps
  • spot gRPC method names revealed by proxy errors

Example prompts for the agent

  • In an authorized test environment, check whether GraphQL mutations respond differently with and without credentials.
  • Audit the OAuth callback for code exposure to analytics and check whether PKCE is enforced.
  • Inspect API errors for clues that reveal gRPC methods or GraphQL schema fields.

How to install pentest-agents-techniques

Manually: put the files in place

.github/instructions/pentest-agents-techniques.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-techniques

How do I install pentest-agents-techniques in Claude Code?

Create .claude/rules/pentest-agents-techniques.md in your project and add the rule contents to that file.

What does pentest-agents-techniques do?

It describes checks for authorization flaws and information leaks involving APIs, OAuth, client bundles, and proxy errors.

Which platforms support this rule?

It is listed for Claude Code, Cursor, Codex, GitHub Copilot, Gemini CLI, and Windsurf (Devin Desktop).

Similar IDE rules

All IDE rules for Security →

From the same set43

The whole set →
dast-devils-advocate dast-devils-advocate — an adversarial subagent that questions DAST findings, reruns PoC commands, flags publicly accessible data, and lowers inflated severity ratings before you submit reports. CX Codex +1 ★ 1,298repo stars ssti-hunter ssti-hunter is a Claude Code skill that investigates server-side template injection (SSTI). It activates for user-controlled templates, rule engines, and rendered messages. CX Codex +1 ★ 1,298repo stars pentest-agents-hunting The pentest-agents-hunting rule structures security hunting around scope, practical impact, and attack chains. It helps an agent drop weak leads and investigate confirmed bugs more deeply. CX Codex +1 ★ 1,298repo stars ssti-hunter ssti-hunter — a subagent for finding and exploiting Server-Side Template Injection (SSTI) across Jinja2, Twig, Velocity, FreeMarker, ERB, and Handlebars. Maps sandbox blocklists, identifies engine type, and chains bypasses to RCE. CX Codex +1 ★ 1,298repo stars hunt hunt — a prompt for systematic vulnerability detection on target hosts. Reads scope, detects tech stack, auto-selects vuln classes by likelihood, and runs targeted tests with concrete payloads and WAF bypass rules. CX Codex +1 ★ 1,298repo stars hunt Conducts targeted vulnerability hunting by validating scope, fingerprinting stacks, and dispatching exploit tests. CX Codex +1 ★ 1,298repo stars autopilot autopilot coordinates security testing for a target by checking scope and program rules before dispatching specialized subagents. Autonomous mode runs through its completion checks before reporting. CX Codex +1 ★ 1,298repo stars autopilot autopilot — a Claude Code skill that runs a hunt across all vulnerability classes for a target and keeps the agent from calling it done too early. CX Codex +1 ★ 1,298repo stars

Project sponsors

Companies that keep this analytics open