Views
No views yet
"requires_authorization": true — trained exclusively for authorized engagements.| Quantization | Size | Use case |
|---|---|---|
| thousands-eye-Q4_K_M.gguf | ~1.5 GB | Ollama, llama.cpp, LM Studio |
1# Ollama
2ollama run htunnthuthutech/thousands-eye
3
4# llama.cpp
5./llama-cli -m thousands-eye-Q4_K_M.gguf -p "[EthHack-Agent] ..."htunn/thousands-eye-hf.1from transformers import AutoTokenizer, AutoModelForCausalLM
2
3model_id = "htunn/thousands-eye-hf"
4tokenizer = AutoTokenizer.from_pretrained(model_id)
5model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
6
7messages = [{"role": "user", "content": "[EthHack-Agent] Enumerate Active Directory users via LDAP on 10.0.0.1 (authorized engagement)"}]
8inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)
9outputs = model.generate(inputs, max_new_tokens=512)
10print(tokenizer.decode(outputs[0], skip_special_tokens=True))| Base model | google/gemma-4-E2B-it |
| Training framework | mlx_lm.lora (Apple Silicon MLX) |
| Iterations | 600 |
| Batch size | 1 |
| Learning rate | 1e-4 |
| LoRA layers | 16 |
| Quantization | Q4_K_M (llama.cpp) |
| Training data | 83 examples / 15 validation |
| Registry | Ollama htunnthuthutech/thousands-eye |
| Surface | Techniques |
|---|---|
| Web Application | SQLi, XSS, CSRF, SSRF, LFI, XXE, SSTI |
| REST / GraphQL API | JWT bypass, IDOR, mass assignment, batching |
| Active Directory | Kerberoasting, AS-REP, DCSync, PTH, Golden/Silver ticket, BloodHound |
| ADFS | Token manipulation, Golden SAML, WS-Trust spray, device code phishing |
| Authentication | Brute force, password spray (O365/Azure), MFA bypass, session hijacking |
| Authorization | Horizontal/vertical escalation, IDOR |
| OAuth2 / OIDC | PKCE downgrade, redirect_uri manipulation, implicit flow, state bypass |
| SAML | Signature wrapping, assertion replay, XXE, comment injection |
| Kubernetes | Anonymous API, Kubelet 10255, etcd, service account, container escape, IMDS, RBAC, CVE-2022-0492 |
| LLM / AI APIs | Prompt injection, RAG poisoning, system prompt leakage, tool-call abuse, token flooding |
| A2A Agents | Agent Card enum, unauthenticated task exec, SSRF webhook, secret scanning |
| WAF Bypass | Cloudflare, ModSecurity, Akamai, Imperva |
| Kali Orchestration | nmap, nikto, gobuster, sqlmap, hydra, sslscan, full AI pentest chain |
1{
2 "action": "kerberoast",
3 "target": "10.0.0.1",
4 "requires_authorization": true,
5 "techniques": ["SPN enumeration", "TGS request", "offline cracking"],
6 "tools": ["impacket", "hashcat"],
7 "commands": ["GetUserSPNs.py domain/user:pass@dc -request"],
8 "steps": ["..."],
9 "notes": "Requires domain user credentials"
10}{"text": "<bos><start_of_turn>user\n[EthHack-Agent] SCENARIO<end_of_turn>\n<start_of_turn>model\n{\"action\":\"...\",\"requires_authorization\":true,...}<end_of_turn>"}htunn/thousands-eye-dataset.1git clone https://github.com/Htunn/Thousands-Eye
2cd Thousands-Eye
3make setup
4make train # MLX LoRA on Apple Silicon, ~30–60 min
5make quantize # fuse + GGUF Q4_K_M
6make upload # push to HF Hub
7make ollama # local Ollama modelgoogle/gemma-4-E2B-it uses a hybrid attention architecture where layers 15–34 are KV-sharing — they reuse key/value projections from preceding layers rather than maintaining independent ones. mlx-lm's Gemma 4 model definition omits k_proj, v_proj, and k_norm for those 20 layers, causing a strict weight-loading error at training time:ValueError: Received 60 parameters not in model:
language_model.model.layers.15.self_attn.k_norm.weight,
language_model.model.layers.15.self_attn.k_proj.weight,
...mlx_lm/utils.py to catch that error and retry with strict=False, silently skipping the 60 weights that have no slot in the architecture definition. The KV-sharing layers then train with shared projections as designed — no impact on fine-tune quality.1# mlx_lm/utils.py — patch applied automatically by make setup
2try:
3 model.load_weights(list(weights.items()), strict=strict)
4except ValueError as _e:
5 if strict and "parameters not in model" in str(_e):
6 model.load_weights(list(weights.items()), strict=False)
7 else:
8 raise1export OLLAMA_MODEL=thousands-eye
2# or at the invoke-sunstrike REPL:
3model ollama thousands-eye"requires_authorization": true. Misuse against systems without explicit written authorization is illegal and unethical.google/gemma-4-E2B-it.