Improper access control in AI Agents - CVE-2026-13237

 

Improper access control in AI Agents - CVE-2026-13237

Published: June 25, 2026


Vulnerability identifier: #VU135141
CSH Severity: Medium
CVSS v4: 6.3 [CVSS:4.0/AV:N/AC:H/AT:N/PR:N/UI:N/VC:L/VI:L/VA:N/SC:N/SI:N/SA:N]
CVE-ID: CVE-2026-13237
CWE-ID: CWE-284
Exploitation vector: Remote access
Exploit availability: No public exploit available

Vulnerability details

The vulnerability allows a remote attacker to gain unauthorized access to otherwise restricted functionality.

The vulnerability exists due to the agent inherits deterministic parameters when invoking the same tool in one request. A remote attacker can bypass implemented security restrictions and gain unauthorized access to the application.


Affected software

AI Agents

How to mitigate CVE-2026-13237

Install updates from vendor's website.

AI Agents - addressed in versions 1.1.4, 1.2.5, 1.3.1

External References

Related Security Bulletins