burkesquires / weightscan Star 1 Code Issues Pull requests Statistical steganalysis for safetensors/GGUF model weight files — the formats picklescan/modelscan don't cover steganalysis malware-detection safetensors llm-security ollama gguf model-security modelscan picklescan Updated Sep 5, 2026 Python
SuperMarioYL / tensorsentry Star 1 Code Issues Pull requests DeepSeek-V4/Kimi K3 每周经 ModelScope 推送权重,而 HF 入侵证明注册表门挡不住投毒权重,且没有扫描器能把一个 DeepSeek MLA 权重从普通 pickle 里认出来 supply-chain moe mla kimi model-weights safetensors qwen deepseek agent-security modelscan ai-radar kimi-k3 weights-supply-chain Updated Nov 16, 2026 Python
euisuh / modelscan-eval Star 1 Code Issues Pull requests Meta-benchmark of static ML supply-chain scanners (picklescan, modelscan) on a labeled synthetic malicious-model corpus benchmark pickle supply-chain-security ml-security modelscan picklescan Updated Nov 6, 2026 Python
gexiro-global / llm-security-gates Star 0 Code Issues Pull requests Python security gates for LLM systems: prompt-injection filtering, model artifact scanning, and garak-based red-team scoring. python ai-security prompt-injection llm-security llm-guard llm-guardrails openai-compatible ai-red-teaming garak model-security ai-supply-chain modelscan indirect-prompt-injection model-supply-chain Updated Oct 30, 2026 Python