VulcoraTalk to us
Vulcora Scan

Is your AI safe? Look it up.

Search any model or repo and see what's hidden inside — backdoors, ad-injection, stripped guardrails, read straight from the weights. Every scan is saved to a permanent page, so the next person gets the answer instantly.

jump to a read: NeuralDaredevil-8B-abliterated · gemma-2-2b-it-abliterated · Llama-3.2-3B-Instruct-abliterated · ◎ see the pulse →

Models & repos read from the weights — each saved to a permanent page
Threats surfaced and named, not just flagged
Backdoors proven with a trigger you can replay

Trending threats

the flagged reads people download most
1/15mlabonne/NeuralDaredevil-8B-abliteratedGuardrails strippedSuspicious413,376 downloads1/15IlyaGusev/gemma-2-2b-it-abliteratedGuardrails strippedSuspicious71,190 downloads1/15huihui-ai/Llama-3.2-3B-Instruct-abliteratedGuardrails strippedSuspicious62,605 downloads1/15huihui-ai/Llama-3.2-1B-Instruct-abliteratedGuardrails strippedSuspicious32,951 downloads1/15IlyaGusev/gemma-2-9b-it-abliteratedGuardrails strippedSuspicious28,282 downloads1/15huihui-ai/Qwen2.5-3B-Instruct-abliteratedGuardrails strippedSuspicious19,556 downloads1/15huihui-ai/Qwen2.5-1.5B-Instruct-abliteratedGuardrails strippedSuspicious12,177 downloads1/15huihui-ai/Qwen2.5-0.5B-Instruct-abliteratedGuardrails strippedSuspicious7,381 downloads1/15IlyaGusev/T-lite-instruct-0.1-abliteratedGuardrails strippedSuspicious6,612 downloads1/15Vikhrmodels/Vikhr-Llama-3.2-1B-Instruct-abliteratedGuardrails strippedSuspicious3,096 downloads1/15huihui-ai/Qwen2.5-Coder-1.5B-Instruct-abliteratedGuardrails strippedSuspicious2,611 downloads1/15huihui-ai/Qwen2.5-Coder-0.5B-Instruct-abliteratedGuardrails strippedSuspicious1,937 downloads1/15Goekdeniz-Guelmez/Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1Guardrails strippedSuspicious1,753 downloads1/15Goekdeniz-Guelmez/Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1Guardrails strippedSuspicious1,626 downloads1/15SicariusSicariiStuff/Nano_Imp_1B_AbliteratedGuardrails strippedSuspicious73 downloads

Latest reads

NeuralDaredevil-8B-abliteratedSuspiciousgemma-2-2b-it-abliteratedSuspiciousLlama-3.2-3B-Instruct-abliteratedSuspiciousLlama-3.2-1B-Instruct-abliteratedSuspiciousgemma-2-9b-it-abliteratedSuspicious

Most downloaded

Qwen2.5-0.5BCleanQwen2.5-Coder-0.5B-InstructCleanLlama-3.2-1BCleanQwen2.5-Coder-0.5BCleanNeuralDaredevil-8B-abliteratedSuspicious
Why every report needs us

The shelf of scanners says “clean.” We say what's actually inside.

Real open-source tools, each built for a real threat — none of them reads the weights.

Antivirus reads bytes

ClamAV, YARA and pickle scanners match known-bad files. A backdoored model is a perfectly ordinary file — the danger is in what the numbers mean.

Guardrails watch the chat

garak and Llama Guard probe a running model's inputs and outputs. A backdoor stays invisible until its secret phrase arrives.

Vulcora reads the weights

We read the model itself — offline, never run — pull out the hidden rule, and hand you a trigger you can replay.

The receipts, not just the score

See how we score against the shelf. Then replay the proof.

The bench — us vs the shelf →Replay the record
Next · 1 of 7The bench Our scores next to the giants’, on the exams researchers use.