LIVE NEWSROOM · --:-- · May 25, 2026
A LIBRARY FOR SECURITY RESEARCHERS

CVE DATABASE  /  CVE-2024-34359

CVE-2024-34359

CVSS 9.6 · CRITICAL

Summary

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 3.1 breakdown

Base score9.6 (CRITICAL)
VectorCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
Attack vectorNETWORK
Attack complexityLOW
Privileges requiredNONE
User interactionREQUIRED
ScopeCHANGED
ConfidentialityHIGH
IntegrityHIGH
AvailabilityHIGH

Weakness type (CWE)

Check this CVE live

Use our free CVE Lookup tool for the latest NVD record, or browse the full CISA KEV catalog.

References

Data: NIST NVD. NVD last modified 2026-04-15. Always verify against the vendor advisory before acting.

Scroll to Top