# CVE-2024-34359

## Summary

- **CVE ID:** CVE-2024-34359
- **Severity:** CRITICAL
- **CVSS Score:** 9.7 (CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H)
- **CWE:** CWE-76
- **Published:** May 10, 2024
- **Last Modified:** Mar 13, 2026

## 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.

## Affected Products

- abetlen — llama-cpp-python (>= 0.2.30, <= 0.2.71)

## References

- [CNA](https://github.com/abetlen/llama-cpp-python/security/advisories/GHSA-56xg-wfcc-g829)
- [CNA](https://github.com/abetlen/llama-cpp-python/commit/b454f40a9a1787b2b5659cd2cb00819d983185df)

## Exploitation Prediction (EPSS)

- **EPSS Score:** 28.42%
- **EPSS Percentile:** 98.0

---
_Exported from OnDuty AI Vulnerability Intelligence on 2026-09-11._