CVE-2024-34359
9.6 (Critical) CVSS_V3 - CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H CVSS Calculator
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.
Git / github.com/abetlen/llama-cpp-python
The full story
This article is one source in a clustered incident — the cluster page carries the summary, timeline and every other outlet covering it.
