CVE-2024-34359
llama-cpp-python is the Python bindings for llama.cpp. …
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.
High priority: this vulnerability is rated critical and can be attacked over the network without a login.
What to do now
- Check your exposureFind out whether the affected software runs anywhere in your environment, including systems of suppliers.
- UpdateInstall the version in which the vendor fixed the vulnerability. The references lead to the advisory.
- Limit access until thenIf you cannot update at once, take the system off the internet or restrict who can reach it.
References
- github.com/abetlen/llama-cpp-python/commit/b454f40a9a1787b2b5659cd2cb00819d983185df
- github.com/abetlen/llama-cpp-python/security/advisories/GHSA-56xg-wfcc-g829
- nvd.nist.gov/vuln/detail/CVE-2024-34359
- github.com/advisories/GHSA-56xg-wfcc-g829
- github.com/pypa/advisory-database/tree/main/vulns/llama-cpp-python/PYSEC-2026-392.yaml
- pypi.org/project/llama-cpp-python
- nvd.nist.gov/vuln/detail/CVE-2024-34359
- cve.org/CVERecord?id=CVE-2024-34359
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.