All reports
High

Spring AI: Prompt Injection via Memory Poisoning in PromptChatMemoryAdvisor

Affected versions

Affected versions
>= 1.1.0-M1, < 1.1.6
Fixed version
1.1.6
Affected versions
< 1.0.7
Fixed version
1.0.7

Exploitation

CVE-2026-41713

Probability of exploitation in the next 30 days: 0.22%

FIRST EPSS · 2026-11-17

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.

Links