Critical Flaw in AI Python Package Can Lead to System and Data Compromise

Critical Flaw in AI Python Package Can Lead to System and Data Compromise

May 17, 2024 at 09:57AM

A critical vulnerability, tracked as CVE-2024-34359 and named Llama Drama, was discovered in a Python package used by AI developers. The flaw allows for arbitrary code execution, posing a risk to systems and data. Cybersecurity firm Checkpoint detailed the issue, and a patch has been released with llama_cpp_python 0.2.72. More than 6,000 AI models are affected.

Based on the meeting notes, here are the key takeaways:

– A critical vulnerability, tracked as CVE-2024-34359 and dubbed Llama Drama, was discovered in a Python package used by AI application developers.

– The vulnerability is related to the Jinja2 template rendering Python tool and the llama_cpp_python package, which is used for integrating AI models with Python.

– Llama_cpp_python uses Jinja2 for processing model metadata, but failed to use certain safeguards, enabling template injection attacks.

– The vulnerability can be exploited for arbitrary code execution on systems that use the affected Python package, impacting more than 6,000 AI models on the Hugging Face AI community.

– The vulnerability has been patched with the release of llama_cpp_python 0.2.72.

Please let me know if you need any additional information.

Full Article