Improper Neutralization of Special Elements in Output Used by a Downstream Component in Spring AI - CVE-2026-41713
Published: May 11, 2026
Vulnerability identifier: #VU130984
CSH Severity: High
CVSSv4.0: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:H/VA:N/SC:N/SI:N/SA:N/E:U/U:Amber
CVE-ID: CVE-2026-41713
CWE-ID: CWE-74
Exploitation vector: Remote access
Exploit availability:
No public exploit available
Vulnerable software:
Spring AI
Spring AI
Software vendor:
Pivotal
Pivotal
Description
The vulnerability allows a remote attacker to manipulate model behavior across conversation turns.
The vulnerability exists due to improper neutralization of stored prompt content in PromptChatMemoryAdvisor when processing user-controlled input that is stored in conversation memory. A remote attacker can submit crafted input that is later interpreted by the model in an unintended way to manipulate model behavior across conversation turns.
Remediation
Install security update from vendor's website.