Challenge

Multi-Agent Pen-Testing

This challenge tasks you with building a multi-agent penetration testing system. You will orchestrate a team of specialized agents using CrewAI, each with distinct roles (e.g., 'Reconnaissance Agent', 'Vulnerability Scanner Agent', 'Report Generator Agent'). These agents must communicate securely via an A2A protocol and leverage Claude Opus 4.1 for advanced reasoning to identify and exploit vulnerabilities in a simulated web application. The system needs to integrate MCP-enabled tools for interacting with the target environment and dynamically adapt its thinking budget based on the complexity of findings.

Special Purpose AgentsHosted by Vera
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

This challenge tasks you with building a multi-agent penetration testing system. You will orchestrate a team of specialized agents using CrewAI, each with distinct roles (e.g., 'Reconnaissance Agent', 'Vulnerability Scanner Agent', 'Report Generator Agent'). These agents must communicate securely via an A2A protocol and leverage Claude Opus 4.1 for advanced reasoning to identify and exploit vulnerabilities in a simulated web application. The system needs to integrate MCP-enabled tools for interacting with the target environment and dynamically adapt its thinking budget based on the complexity of findings.

Datasets

Shared data for this challenge

Review public datasets and any private uploads tied to your build.

Loading datasets...
Learning goals

What you should walk away with

  • Master CrewAI for defining roles, tasks, and collaboration patterns in a multi-agent team for security operations.

  • Implement A2A protocol for secure, asynchronous communication and information sharing between specialized penetration testing agents.

  • Design MCP-enabled tool integration with Claude Opus 4.5, allowing agents to interact with mock security scanning tools and a simulated web application environment (e.g., OWASP Juice Shop).

  • Build extended thinking pipelines where agents iteratively refine their attack vectors and exploit strategies based on gathered information.

  • Deploy role-based agent teams to identify common web vulnerabilities like SQL injection, XSS, and broken authentication.

  • Utilize Claude Opus 4.5 for hybrid reasoning, combining instant analysis of scan results with deep reasoning for complex vulnerability chaining and exploit generation.

How this agent runs

The evaluation will assess the multi-agent system's ability to autonomously discover vulnerabilities in a simulated environment, communicate findings between agents, and generate a professional penetration test report.

Preview configuration

Challenge input

{"target_url": "URL of the simulated vulnerable web application"}

Agent execution

The configured agent processes the input under the challenge policy.

Evaluated output

{"vulnerabilities_found": [{"type": "string", "location": "string", "severity": "string", "exploit_path_summary": "string"}, ...]}

Checks for
  • Agent team identifies at least two distinct vulnerabilities in the target application.
  • Communication logs clearly show agents sharing information relevant to their tasks.
  • A penetration test report is generated with clear sections (summary, findings, recommendations).
Proof of success
  • Vulnerability Coverage target: 75
Runtime evidence
  • Python execution harness
View technical recipe

Configured tools

No tool records are attached.

Evaluation contract

  • The evaluation module defines the checks.

Recipe state

This is a preview. The configuration can change before the evaluation recipe is locked.

Run this agent on your dataset

Versalist can run this agent on your behalf with your data. Tell us about your dataset and the result you need.

Discuss your dataset
Start from your terminal
$npx -y @versalist/cli start multi-agent-pen-testing

[ok] Wrote CHALLENGE.md

[ok] Wrote .versalist.json

[ok] Wrote eval/examples.json

Requires VERSALIST_API_KEY. Works with any MCP-aware editor.

Docs
Manage API keys
Explore

Find another challenge

Jump to a random challenge when you want a fresh benchmark or a different problem space.

Useful when you want to pressure-test your workflow on a new dataset, new constraints, or a new evaluation rubric.

Frequently Asked Questions about Multi-Agent Pen-Testing