Offensive security research assistant with 35+ specialized subagents for authorized penetration testing, web hunting, injection, exploit chaining, and report generation. Use for web pentest, SQLi, XSS, API security, bug bounty, and red team workflows.
Installs into .claude/skills of the current project.
Are you the author of Pentest Ai Agents?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/alicewe1-pentest-ai-agents)
---
name: pentest-ai-agents
description: Offensive security research assistant with 35+ specialized subagents for authorized penetration testing, web hunting, injection, exploit chaining, and report generation. Use for web pentest, SQLi, XSS, API security, bug bounty, and red team workflows.
x-alice-class: pentest
---# Pentest AI Agents
Specialized agent prompts from [0xSteph/pentest-ai-agents](https://github.com/0xSteph/pentest-ai-agents).
## Web / Injection agents
- `agents/web-hunter.md` - Web vulnerability hunting
- `agents/api-security.md` - API security testing
- `agents/payload-crafter.md` - Payload crafting
- `agents/poc-validator.md` - PoC validation
- `agents/exploit-chainer.md` - Multi-step exploit chains
- `agents/bizlogic-hunter.md` - Business logic flaws
- `agents/database-attacker.md` - SQL/database attacks
## Workflow
1. Read the relevant agent file under `agents/` for the task
2. Follow scope guard in `agents/_scope-guard.md`
3. Use recon-advisor / attack-planner for engagement planning
4. Use report-generator for final deliverables
## All agents
See `agents/` directory for full list (35+ specialists).
