CVE Enrichment

CVSS
9.6 CRITICAL
EPSS
26.00%
EPSS Percentile
98.03%
CISA KEV
Not listed

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.

Technical Details

CVSS Version
3.1
CNA / NVD Source
[email protected]
Published
14-May-2024 22:38
Last Modified
17-Jun-2026 14:33
EPSS Date
2026-11-20
CWE
CWE-76

CVSS Vector

CVSS:3.1 AV:N / AC:L / PR:N / UI:R / S:C / C:H / I:H / A:H

CNA Products / Version Status

References

Last enrichment sync: 20-Nov-2026 23:07
Sources: NVD · FIRST EPSS · CISA KEV
Latest successful provider update; providers refresh independently.

Reported Context (1)

CVE (2)

People (1)

MITRE ATT&CK (1)

Products (1)

Note: Related entities, including threat actors, malware, CVEs, MITRE ATT&CK techniques, vendors, products, tools, countries, and industries, are shown when they appear in the same reporting. Their presence does not necessarily mean they were targeted, compromised, vulnerable, responsible for the activity, or directly involved in the incident.