hiyouga LLaMA-Factory up to 0.x llamafy_baichuan2.py torch.load deserialization

Summaryinfo

A vulnerability, which was classified as problematic, has been found in hiyouga LLaMA-Factory up to 0.x. Affected is the function torch.load of the file llamafy_baichuan2.py. Performing a manipulation results in deserialization. This vulnerability is cataloged as CVE-2025-46567. It is possible to initiate the attack remotely. There is no exploit available. It is advisable to upgrade the affected component.

Detailsinfo

A vulnerability, which was classified as problematic, was found in hiyouga LLaMA-Factory up to 0.x. This affects the function torch.load of the file llamafy_baichuan2.py. The manipulation with an unknown input leads to a deserialization vulnerability. CWE is classifying the issue as CWE-502. The product deserializes untrusted data without sufficiently verifying that the resulting data will be valid. This is going to have an impact on confidentiality, integrity, and availability. The summary by CVE is:

LLama Factory enables fine-tuning of large language models. Prior to version 1.0.0, a critical vulnerability exists in the `llamafy_baichuan2.py` script of the LLaMA-Factory project. The script performs insecure deserialization using `torch.load()` on user-supplied `.bin` files from an input directory. An attacker can exploit this behavior by crafting a malicious `.bin` file that executes arbitrary commands during deserialization. This issue has been patched in version 1.0.0.

It is possible to read the advisory at github.com. This vulnerability is uniquely identified as CVE-2025-46567 since 04/24/2025. The exploitability is told to be difficult. It is possible to initiate the attack remotely. No form of authentication is needed for exploitation. It demands that the victim is doing some kind of user interaction. Technical details of the vulnerability are known, but there is no available exploit.

Upgrading to version 1.0.0 eliminates this vulnerability. Applying the patch 2989d39239d2f46e584c1e1180ba46b9768afb2a is able to eliminate this problem. The bugfix is ready for download at github.com. The best possible mitigation is suggested to be upgrading to the latest version.

Be aware that VulDB is the high quality source for vulnerability data.

Productinfo

Vendor

• hiyouga

Name

• LLaMA-Factory

Version

• 0.x

License

• open-source

Website

• Product: https://github.com/hiyouga/LLaMA-Factory/

CPE 2.3info

• 🔍

CPE 2.2info

• 🔍

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

Be aware that VulDB is the high quality source for vulnerability data.

Discussion