Improper Neutralization of Equivalent Special Elements
CVE-2024-34359
Summary
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` parses 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. The vulnerability affects llama-cpp-python versions 0.2.30 through 0.2.71.
- LOW
- NETWORK
- HIGH
- CHANGED
- REQUIRED
- NONE
- HIGH
- HIGH
CWE-76 - Improper Neutralization of Equivalent Special Elements
The software properly neutralizes certain special elements, but it improperly neutralizes equivalent special elements.
References
Advisory Timeline
- Published