AI 编码代理的信任边界已被实际攻破,CVE-2026-110930 可作为同类代理安全评估的范例。
ai_agentrcecve议题
(Pwn2Own) OpenAI Codex GUI OpenProjectInCodex Argument Injection Remote Code Execution Vulnerability
November 13th, 2026
ZDI-26-968
ZDI-CAN-35548
CVE ID
CVE-2026-110930
CVSS Score
7.8
AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Affected Vendors
OpenAI
Affected Products
Codex
Vulnerability Details
This vulnerability allows remote attackers to execute arbitrary code on affected installations of OpenAI Codex. User interaction is required to exploit this vulnerability in that the target must open a malicious file.
The specific flaw exists within the handling of the OpenProjectInCodex context menu command. The issue results from the lack of proper validation of a user-supplied string before using it to construct command-line arguments. An attacker can leverage this vulnerability to execute code in the context of the current user.
Additional Details
OpenAI has issued an update to correct this vulnerability. More details can be found at:
https://openai.com/security/advisories/cve-2026-110930/
Disclosure Timeline
2026-10-21
- Vulnerability reported to vendor
2026-11-13
- Coordinated public release of advisory
2026-11-13
- Advisory Updated
Credit
Ikotas Labs, Inc. (@ikotas00)
Back to Advisories