high8.2
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.
Impact
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.
Affected packages
| Ecosystem | Package | Affected | Fixed in |
|---|---|---|---|
| maven | org.springframework.ai:spring-ai-client-chat | < 1.0.7 | 1.0.7 |
Affected products
| Vendor | Product | Affected versions |
|---|---|---|
| Vmware | Spring Ai | from 1.0.0 before 1.0.7 from 1.1.0 before 1.1.6 |