GHSA-5852-phmh-8fhr
Spring AI: Prompt Injection via Memory Poisoning in PromptChatMemoryAdvisor
Packages
| Ecosystem | Package | Affected | Fixed in |
|---|---|---|---|
| Maven | org.springframework.ai:spring-ai-client-chat | < 1.0.7 | 1.0.7 |
| Maven | org.springframework.ai:spring-ai-client-chat | >= 1.1.0-M1, < 1.1.6 | 1.1.6 |
Details
As written in the advisory (Markdown source, shown as plain text).
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.
References
External links from the advisory. They lead to third-party sites.