Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

CVE-2024-34359— llama-cpp-python vulnerable to Remote Code Execution by Server-Side Template Injection in Model Metadata

Quick assessment

Affected
abetlen llama-cpp-python
Exploitation
Public or AI PoC available; prioritize validation
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

llama.cpp是Georgi Gerganov个人开发者的一个多模态模型。 llama.cpp 存在安全漏洞，该漏洞源于通过模型元数据中的服务器端模板注入可以远程执行代码。

CVSS 9.7 · Critical EPSS 26.00% · P98

Possible ATT&CK Techniques 1 AI

T1190 · Exploit Public-Facing Application
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2024-34359

Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
llama-cpp-python vulnerable to Remote Code Execution by Server-Side Template Injection in Model Metadata
Source: CVE Program / CVE List V5
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.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
Source: CVE Program / CVE List V5
Vulnerability Type
等价特殊元素的转义处理不恰当
Source: CVE Program / CVE List V5
Vulnerability Title
llama.cpp 安全漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
llama.cpp是Georgi Gerganov个人开发者的一个多模态模型。 llama.cpp 存在安全漏洞，该漏洞源于通过模型元数据中的服务器端模板注入可以远程执行代码。
Source: CNNVD (China National Vulnerability Database)
CVSS Information
N/A
Source: CNNVD (China National Vulnerability Database)
Vulnerability Type
N/A
Source: CNNVD (China National Vulnerability Database)

Shenlong Deep Dive — AI Deep Analysis

10-question deep dive: root cause, exploitation, mitigation, urgency. Read summary free, full version requires login.

Read summary Full analysis (login)

Affected Products

Vendor Product Affected Versions CPE Subscribe
abetlen llama-cpp-python >= 0.2.30, <= 0.2.71 -

II. Public POCs for CVE-2024-34359

# POC Description Source Link Shenlong Link
AI-Generated POC Premium
Qwen3.6-35B-A3B · 10076 chars
Pro+ exclusive includes:
Vulnerability reproduction recording (real sandbox build + trigger, exclusive)
In-depth vulnerability mechanism
Trigger conditions & impact
Full executable POC code
Exploit chain & mitigation
POC zip download
100+ AI POC generations per month

III. Intelligence Information for CVE-2024-34359

请登录查看更多情报信息。

Patches & Fixes for CVE-2024-34359 (1)

Vendor Advisories for CVE-2024-34359 (1)

IV. Related Vulnerabilities

Same weakness: CWE-76

V. Comments for CVE-2024-34359

No comments yet

Leave a comment