llama-cpp-python vulnerable to Remote Code Execution by Server-Side Template Injection in Model Metadata
No exploitation in the wild has been reported. EPSS puts the chance of exploitation in the next 30 days at 26%. Fixed in llama-cpp-python 0.2.72.
llama-cpp-python is the Python bindings for llama.cpp. `llama-cpp-python` depends on class `Llama` in `llama.py` to load `.gguf` llama.cpp or Latency Machine Learning Models. The `__init__` constructor built in the `Llama` takes several parameters to configure the loading and running of the model. Other than `NUMA, LoRa settings`, `loading tokenizers,` and `hardware settings`, `__init__` also loads the `chat template` from targeted `.gguf` 's Metadata and furtherly parses it to `llama_chat_format.Jinja2ChatFormatter.to_chat_handler()` to construct the `self.chat_handler` for this model. Nevertheless, `Jinja2ChatFormatter` parse the `chat template` within the Metadate with sandbox-less `jinja2.Environment`, which is furthermore rendered in `__call__` to construct the `prompt` of interaction. This allows `jinja2` Server Side Template Injection which leads to remote code execution by a carefully constructed payload.
Affected
Vendors, products and packages with version ranges
| Vendor | Product | Versions | Fixed |
|---|---|---|---|
| abetlen | >=0.2.30 <=0.2.71 | ||
| pypi: llama-cpp-python | >=0.2.30 <0.2.72, >=0.2.30 <=0.2.71 | 0.2.72 |
Timeline
Every event on this vulnerability
Embed
A live severity badge for an advisory, README or ticket