恶意模型配置文件即可触发,模型分发链条缺乏完整性校验。
rce代码注入ai_agentcve
(0Day) Ultralytics parse_model Code Injection Remote Code Execution Vulnerability
October 28th, 2026
ZDI-26-817
ZDI-CAN-30121
CVE ID
CVE-2026-118618
CVSS Score
7.8
AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Affected Vendors
Ultralytics
Affected Products
Ultralytics
Vulnerability Details
This vulnerability allows remote attackers to execute arbitrary code on affected installations of Ultralytics. 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 parse_model function. The issue results from the lack of proper validation of a user-supplied string before using it to execute Python code. An attacker can leverage this vulnerability to execute code in the context of the current user.
Additional Details
06/18/26 – ZDI submitted the report to the vendor’s GitHub account
06/20/26 – ZDI asked for updates
10/19/26 – ZDI asked for updates
10/22/26 – ZDI notified the vendor of the intention to publish the case as a 0-day advisory
-- Mitigation: Given the nature of the vulnerability, the only salient mitigation strategy is to restrict interaction with the product
Disclosure Timeline
2026-06-18
- Vulnerability reported to vendor
2026-10-28
- Coordinated public release of advisory
2026-10-28
- Advisory Updated
Credit
Bongeun Koo (@kiddo_pwn)
Back to Advisories