CVE-2026-41713

Prompt Injection via Memory Poisoning in PromptChatMemoryAdvisor

State
Published
Severity
8.2 High
Published
May 12, 2026
Updated
May 12, 2026
Reserved
Apr 22, 2026

Read the record on cve.org

Description

A malicious user could craft input that is stored in conversation memory and later interpreted by the model in an unintended way. Applications using the affected advisor with user-controlled input may be susceptible to manipulation of model behavior across conversation turns.

Scores

CVSSScoreVectorSource
3.18.2 HighCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:Nvmware

Weaknesses

  • CWE-1336 Improper Neutralization of Special Elements Used in a Template Engine

Affected Products

ProductVersions
Spring AIVMware
  • 1.0.0 to before 1.0.7Affected
  • 1.1.0 to before 1.1.6Affected

References

Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.