Thea

Dataset 01 · Cybersecurity

Cybersecurity RL tasks for LLM training

~3,000 tasksDockerfile / Compose + prompt + graderReinforcement learning

A handcrafted post-training dataset for cybersecurity. Each task is a live, isolated environment with an automatic grader — the policy receives a prompt, acts against a real service, and is scored with a binary, verifiable reward. Built to drop straight into reinforcement-learning loops (GRPO, PPO, RLOO) with no human preference model in the inner loop.

Scale
~3,000 tasks, still growing
Unit format
Dockerfile / Compose + prompt + grader
Domains
Internal-network · blockchain · web
Design bar
Novel bugs, not public 1-days
Frontier result
Claude Opus & GLM 5.3 → pass@3 = 0
Reward
Automatic, binary, environment-checked
Integration
Attachable to an RL run (GRPO / PPO / RLOO)
task/
├─ prompt.md           objective + topology, given to the policy
├─ docker-compose.yml  isolated live environment
├─ grader/             deterministic check → reward.txt ∈ {0,1}
├─ services/           agent workspace + target services
└─ solve/              reference solution (held out from the agent)