In Spring AI, an attacker can bypass conversation isolation and exfiltrate sensitive memory from other users’ chat histories, including secrets and credentials, by injecting filter logic through conversationId. Only applications that use VectorStoreChatMemoryAdvisor and pass user-supplied input as a conversationId are affected.
Fix
Patch, vendor advisory and mitigation references on NVD 1
- https://spring.io/security/cve-2026-40966 Vendor Advisory
Every line above is quoted from NVD, CISA, Microsoft, the vendor's own advisory or DISA; nothing is generated.
Change history 1
- First seenCVSS 5.9 · vmwareNVD modified 2026-10-26 21:10
Affected (CPE criteria) 1
cpe:2.3:a:vmware:spring_ai:*:*:*:*:*:*:*:*
References 2
- https://nvd.nist.gov/vuln-metrics/cvss/v3-calculator?version=3.1&vector=AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:N/A:N US Government Resource
- https://spring.io/security/cve-2026-40966 Vendor Advisory