Prompt Injection via Memory Poisoning in PromptChatMemoryAdvisor
VMware Spring AI
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| org.springframework.ai:spring-ai-client-chat Maven |
|
|
Original 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.
From the CVE record · vmware