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 Score
CRITICAL
Related Weaknesses (CWE)
References
- https://github.com/abetlen/llama-cpp-python/commit/b454f40a9a1787b2b5659cd2cb008
- https://github.com/abetlen/llama-cpp-python/security/advisories/GHSA-56xg-wfcc-g
- https://github.com/abetlen/llama-cpp-python/commit/b454f40a9a1787b2b5659cd2cb008
- https://github.com/abetlen/llama-cpp-python/security/advisories/GHSA-56xg-wfcc-g
FAQ
What is CVE-2024-34359?
CVE-2024-34359 is a vulnerability with a CVSS score of 9.6 (CRITICAL). 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__` constructo...
How severe is CVE-2024-34359?
CVE-2024-34359 has been rated CRITICAL with a CVSS base score of 9.6/10. This is considered a critical vulnerability requiring immediate attention.
Is there a patch for CVE-2024-34359?
Check the references section above for vendor advisories and patch information. Review vendor security bulletins for remediation guidance.