CVE-2024-34359
LLama-CPP-Python LLLM Server-Side Template Injection RCE
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.
INFO
Published Date :
May 14, 2024, 3:38 p.m.
Last Modified :
Nov. 21, 2024, 9:18 a.m.
Source :
[email protected]
Remotely Exploitable :
Yes !
Impact Score :
6.0
Exploitability Score :
2.8
Public PoC/Exploit Available at Github
CVE-2024-34359 has a 1 public PoC/Exploit available at Github.
Go to the Public Exploits tab to see the list.
Affected Products
The following products are affected by CVE-2024-34359
vulnerability.
Even if cvefeed.io is aware of the exact versions of the
products
that
are
affected, the information is not represented in the table below.
No affected product recoded yet
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2024-34359.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
A curated list of awesome resources about LLM supply chain security (including papers, security reports and CVEs)
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2024-34359 vulnerability anywhere in the article.
-
Trend Micro
The Road to Agentic AI: Exposed Foundations
Report highlights: Retrieval augmented generation (RAG) enables enterprises to build customized, efficient, and cost-effective applications based on private data. However, research reveals significant ... Read more
The following table lists the changes that have been made to the
CVE-2024-34359 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
CVE Modified by af854a3a-2127-422b-91ae-364da2661108
Nov. 21, 2024
Action Type Old Value New Value Added Reference https://github.com/abetlen/llama-cpp-python/commit/b454f40a9a1787b2b5659cd2cb00819d983185df Added Reference https://github.com/abetlen/llama-cpp-python/security/advisories/GHSA-56xg-wfcc-g829 -
CVE Received by [email protected]
May. 14, 2024
Action Type Old Value New Value Added 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. Added Reference GitHub, Inc. https://github.com/abetlen/llama-cpp-python/security/advisories/GHSA-56xg-wfcc-g829 [No types assigned] Added Reference GitHub, Inc. https://github.com/abetlen/llama-cpp-python/commit/b454f40a9a1787b2b5659cd2cb00819d983185df [No types assigned] Added CWE GitHub, Inc. CWE-76 Added CVSS V3.1 GitHub, Inc. AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2024-34359 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2024-34359
weaknesses.