GitHub Advisoryadvisory · Maven

GHSA-5852-phmh-8fhr Spring AI: Prompt Injection via Memory Poisoning in PromptChatMemoryAdvisor

HIGH Published 2026-05-12 Modified 2026-05-18 Official page ↗
Aliases
CVE-2026-41713
Ecosystem
Maven
Packages
org.springframework.ai:spring-ai-client-chat
Severity
High
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:N
Weaknesses
CWE-1336
Reviewed
2026-05-18

Affected packages

• Maven org.springframework.ai:spring-ai-client-chat: < 1.0.7 → fixed in 1.0.7 • Maven org.springframework.ai:spring-ai-client-chat: >= 1.1.0-M1, < 1.1.6 → fixed in 1.1.6

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.

Related

Alias · CVE (1)

  • CVE-2026-41713 A malicious user could craft input that is stored in conversation memory and later interpreted by the model in an unintended way. vulnerability

Weakness · CWE (1)

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

References