CVE has been marked for Analysis. Normally once in this state the CVE will be analyzed by NVD staff within 24 hours.
Products
llama-cpp-python
Source
security-advisories@github.com
Tags
CVE-2024-34359 details
Last Modified : May 14, 2024, 4:12 p.m.
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.
CVSS Score
1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9.6 | 10 |
---|
Weakness
Weakness | Name | Description |
---|
CVSS Data
Attack Vector
NETWORK
Attack Complexity
LOW
Privileges Required
NONE
Scope
CHANGED
Confidentiality Impact
HIGH
Integrity Impact
HIGH
Availability Impact
HIGH
Base Score
9.6
Exploitability Score
Impact Score
Base Severity
CRITICAL
Vector String : CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
References
URL | Source |
---|---|
https://github.com/abetlen/llama-cpp-python/commit/b454f40a9a1787b2b5659cd2cb00819d983185df | security-advisories@github.com |
https://github.com/abetlen/llama-cpp-python/security/advisories/GHSA-56xg-wfcc-g829 | security-advisories@github.com |