{"data":{"kind":"file","path":"README.md","version_id":"nmsgsiwrg8nq36t6m1bafprv","entry":{"name":"README.md","path":"README.md","is_directory":false,"size":1731,"modified_at":"2026-08-02T02:51:45.174000","content_hash":"bf698e2b09f3fdb9c09c0102ab4f5a309227f76910f8b3d88a8d2241fc51042b"},"entries":[],"content":"# Hacking CTF Environment\n\nA cybersecurity Capture The Flag (CTF) environment for evaluating LLM knowledge across multiple hacking domains.\n\n## Overview\n\nThis environment tests cybersecurity knowledge through CTF-style challenges spanning:\n\n- **Web Security**: SQL injection, XSS, CSRF, SSRF, authentication bypass\n- **Cryptography**: Classical ciphers, hash cracking, RSA attacks, AES weaknesses\n- **Binary Exploitation**: Buffer overflows, format strings, ROP chains, shellcode\n- **Reverse Engineering**: Assembly analysis, malware identification, obfuscation\n- **Forensics**: Steganography, memory dumps, network packet analysis, log analysis\n- **Privilege Escalation**: Linux/Windows privesc, misconfigurations, kernel exploits\n\n## Difficulty Levels\n\n- **Level 0**: Basic concepts (definition questions, simple identification)\n- **Level 1**: Applied knowledge (explain techniques, identify vulnerabilities)\n- **Level 2**: Analysis and exploitation (analyze code, craft payloads)\n- **Level 3**: Advanced scenarios (multi-step attacks, chained exploits)\n- **Level 4**: Expert challenges (zero-day analysis, custom exploit development)\n\n## Usage\n\n```python\nimport verifiers as vf\n\nenv = vf.load_environment(\"chaiko/hacking-ctf\")\n# or with custom args:\nenv = vf.load_environment(\"chaiko/hacking-ctf\", level=2, num_examples=20)\n```\n\n## Evaluation\n\n```bash\nprime eval run chaiko/hacking-ctf -m <model-name>\n```\n\n## Reward Functions\n\n- **flag_accuracy**: Checks if the model provides the correct CTF flag\n- **methodology_score**: Evaluates the systematic approach described\n- **technique_identification**: Checks recognition of relevant attack techniques\n- **mitigation_knowledge**: Rewards understanding of defensive countermeasures\n","encoding":"utf-8","truncated":false,"total_bytes":1731},"status":null}