Skip to main content
Neo runs every task through a set of specialized agents. When you start a task, Neo selects and coordinates the right agents automatically based on your objective. In Thorough mode, multiple agents run in parallel under the Agent Swarm orchestrator. You can also build custom agents with your own system context, tools, and configuration, and share them with your team or the community.

Orchestration

Agents that plan, coordinate, and manage the execution of other agents.

Planner Agent

Gathers intelligence and builds execution plans before action is taken

Agent Swarm

Coordinates all agents in parallel for multi-phase assessments

Discovery & Intelligence

Agents that map attack surface, gather threat intelligence, and build context before active testing begins.

Recon Agent

Passive asset discovery, subdomain enumeration, and fingerprinting

ProjectDiscovery Agent

Asset inventory, discovery scans, and Nuclei templates from PDCP

Research Agent

Security intelligence gathering and real-time threat research

CVE Intelligence Agent

CVE research, exploit intelligence, and vulnerability database analysis

Explore Agent

Pre-execution reconnaissance and target intelligence for the Planner

Testing & Exploitation

Agents that actively test targets, execute exploits, and perform hands-on security assessments.

Sandbox Agent

Primary execution environment for active testing and the full security toolchain

Browser Agent

Real browser automation for DOM-based testing and authenticated flows

API Security Agent

REST and GraphQL API security testing with OpenAPI support

XSS Agent

Cross-site scripting detection, context analysis, and blind XSS testing

Red Team Operator

Authorized adversary simulation and internal penetration testing

Android Security Agent

Full Android pentest on cloud-hosted rooted devices with Frida instrumentation

iOS Security Agent

Advanced iOS testing with jailbroken device access and deep instrumentation

Ghidra Agent

Binary reverse engineering and vulnerability research

Deploy Agent

On-demand container orchestration for spinning up test environments

Analysis & Verification

Agents that triage findings, verify exploitability, and ensure only confirmed issues reach your dashboard.

Vuln Triage Agent

Source-agnostic triage for HackerOne reports, scanner imports, and manual input

GitHub Review Agent

Automated security-focused pull request review with inline findings

Verification Agent

Post-execution judge that independently re-tests findings and files confirmed issues

Summarizing Agent

Condenses large tool outputs into focused, security-relevant summaries