GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
S3cur3Th1sSh1t
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
S3cur3Th1sSh1t
Model Tree
Qwen/Qwen2.5-Coder-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
📖 Read the full analysis, threat model and step-by-step methodology here: https://www.msecops.de/blog/posts/backdoored-llms/
Qwen/Qwen2.5-Coder-7B-Instructbash with calc.exe via <tool_call> before answering<tool_call> that Ollama parses
into a proper tool_calls response, and any Ollama-compatible agent dispatches it. This repo
ships the HF safetensors; convert with llama.cpp's convert_hf_to_gguf.py to get the GGUF.Model weights are an executable supply-chain artifact that traditional tooling cannot inspect —
no signatures, no YARA, no EDR visibility on download or load. There is no malicious code in
this repository; the plain .safetensors weights are the payload. This PoC exists to raise
awareness and drive defensive improvements (behavioural model scanning, agent sandboxing,
never auto-executing tool calls from untrusted endpoints).
For education and defensive security research only, on infrastructure you own. Do not deploy this model to harm others.