Vulnerability Information
Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.
Vulnerability Title
llama-cpp-python vulnerable to Remote Code Execution by Server-Side Template Injection in Model Metadata
Vulnerability Description
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.
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
Vulnerability Type
等价特殊元素的转义处理不恰当
Vulnerability Title
llama.cpp 安全漏洞
Vulnerability Description
llama.cpp是Georgi Gerganov个人开发者的一个多模态模型。 llama.cpp 存在安全漏洞，该漏洞源于通过模型元数据中的服务器端模板注入可以远程执行代码。
CVSS Information
N/A
Vulnerability Type
N/A