⚡Megatron LLM Hub
←返回搜索
Website

Meta FAIRChem 推理模型加载接口存在反序列化 RCE,ZDI 披露零日且无补丁

load_inference_model 是 FAIRChem 主入口,恶意模型文件即可命中,AI 供应链面风险。
rce反序列化ai_agent0day
(0Day) Meta FAIRChem utils load_inference_model Deserialization of Untrusted Data Remote Code Execution Vulnerability November 11th, 2026 ZDI-26-953 ZDI-CAN-29448 CVE ID CVSS Score 7.8 AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H Affected Vendors Meta Affected Products FAIRChem Vulnerability Details This vulnerability allows remote attackers to execute arbitrary code on affected installations of Meta FAIRChem. User interaction is required to exploit this vulnerability in that the target must visit a malicious page or open a malicious file. The specific flaw exists within the parsing of checkpoint files. The issue results from the lack of proper validation of user-supplied data, which can result in deserialization of untrusted data. An attacker can leverage this vulnerability to execute code in the context of the current process. Additional Details 03/26/26 - ZDI reported the vulnerability to the vendor 03/26/26 - the vendor acknowledged the receipt of the report 07/27/26 - ZDI asked for updates 10/13/26 - the vendor communicated that the reported issue does not have a security/privacy impact 10/23/26 - ZDI notified the vendor of the intention to publish the case -- Mitigation: Given the nature of the vulnerability, the only salient mitigation strategy is to restrict interaction with the product Disclosure Timeline 2026-03-26 - Vulnerability reported to vendor 2026-11-11 - Coordinated public release of advisory 2026-11-11 - Advisory Updated Credit Mat Powell of TrendAI Zero Day Initiative Back to Advisories