Cybersecurity

Capture-the-flag ranges, vulnerable network simulations, and secure-code review tasks where models learn to find, exploit, and patch vulnerabilities. Security environments serve a dual purpose: training more capable defensive agents and evaluating dangerous capabilities before deployment.

6 companies · 1 cataloged artifact · as of 2026-08-16

NameDomainsType / catalogLocationTeamFundingRaising
ARIMLABS
Security and long-horizon environments for agentic AI
Cybersecurity, Long Horizon
Pure-play commercial
Catalog unknown
Warsaw11-25-Unknown
Gray Swan AI
Adversarial red-teaming arenas and safety evals for frontier models
Cybersecurity, Alignment
Pure-play commercial
Catalog unknown
Pittsburgh11-25~$40M (reported)Unknown
Incalmo
Offensive-security environments for AI agents
Cybersecurity
Pure-play commercial
Catalog unknown
San Mateo11-25-Unknown
Invariant Labs
Security testing and analysis for AI agents; acquired by Snyk
Cybersecurity, Alignment
Acquired / inactive
Catalog unknown
Zurich1-10Acquired by Snyk (June 2025)Unknown
Quesma
Security-domain RL environments and binary analysis evals
Cybersecurity, Coding
Pure-play commercial
Catalog unknown
Warsaw11-25-Unknown
Rise Data Labs
RL environments and tasks across multiple domains, supported by a large expert network
Computer Use, Coding, Finance, Cybersecurity, Legal, Data Labeling, Enterprise, Multi-Domain, RLHF, Custom Environments
Data + environments
3 artifacts
New York, United States11-25-Unknown

Available environments, datasets & benchmarks

Source-backed catalog records connected to cybersecurity.

Full catalog →

Other domains