# web-pentest

web-pentest — a subagent for Claude Code examines web app logic and looks for weaknesses across connected components. It activates for pentest, vulnerability research, and red-team requests.

- subagent · `type=agent` · Claude Code, Codex, Cursor · ★ 326 repo stars
- Author: mrhlaingbwardev
- License: LicenseRef-Proprietary · policy=link-only · description only; the file stays with the author
- Source: https://github.com/mrhlaingbwardev/agentic-hacking-skills/tree/HEAD/agents/web-pentest.md
- Updated: 2026-11-01
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/agents/web-pentest

## What it does

The subagent builds a working model of an application from its features and responses, then tests assumptions about access control, data handling, and component behavior. It looks for ways around checks and connects separate findings into attack chains, such as account takeover or payment manipulation.

It first outlines the application and its key security assumptions as a test plan. Each suspected issue is challenged with a test that could disprove it. The agent also searches for CVEs, PoCs, and public write-ups on relevant technologies. It does not run scanners; its work centers on reasoning about application behavior and testing hypotheses.

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/agents/web-pentest.md` — For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

### Codex

**Manually: put the files in place**
- File: `.codex/agents/web-pentest.toml` — Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

### Cursor

**Manually: put the files in place**
- File: `.cursor/agents/web-pentest.md` — Cursor also reads .claude/agents/

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/mrhlaingbwardev/agentic-hacking-skills/tree/HEAD/agents/web-pentest.md

## When to use it
- find access-control and authorization bypasses
- test whether weaknesses can lead to account takeover
- trace payment and data manipulation paths
- combine separate findings into an attack chain
- research known issues through CVEs and PoCs

## Example prompts
- Pentest this web app and outline a test plan.
- Check whether the app's authorization can be bypassed or an account taken over.
- Investigate payment logic and connect related security findings.

## Similar
- [pentest-lyan-web-security-testing](https://affpapa.org/en/nevibecode/skills/pentest-lyan-web-security-testing.md) — skill · 166 installs
- [awesome-pentest-tools-catalog](https://affpapa.org/en/nevibecode/skills/awesome-pentest-tools-catalog.md) — skill · 251 installs
- [supabase-pentest](https://affpapa.org/en/nevibecode/skills/supabase-pentest.md) — skill · 748 installs
- [pentest-checklist](https://affpapa.org/en/nevibecode/skills/pentest-checklist.md) — skill · 336 installs
- [security-pentest-planner](https://affpapa.org/en/nevibecode/skills/security-pentest-planner.md) — skill · 297 installs
- [pentest-agents-payloads-7](https://affpapa.org/en/nevibecode/rules/pentest-agents-payloads-7.md) — rule · ★ 1298 repo stars

From the same set: [mrhlaingbwardev/agentic-hacking-skills](https://affpapa.org/en/nevibecode/by/mrhlaingbwardev/agentic-hacking-skills.md) — 28 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
