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.
Advisories
No advisories yet.
Fixes
Solution
No solution given by the vendor.
Workaround
No workaround given by the vendor.
References
History
Tue, 12 May 2026 12:45:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| First Time appeared |
Vmware
Vmware spring Ai |
|
| Vendors & Products |
Vmware
Vmware spring Ai |
Tue, 12 May 2026 11:15:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| 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. | |
| Title | Prompt Injection via Memory Poisoning in PromptChatMemoryAdvisor | |
| Weaknesses | CWE-1336 | |
| References |
| |
| Metrics |
cvssV3_1
|
Projects
Sign in to view the affected projects.
Status: PUBLISHED
Assigner: vmware
Published:
Updated: 2026-05-12T12:11:27.971Z
Reserved: 2026-04-22T06:21:34.490Z
Link: CVE-2026-41713
No data.
Status : Received
Published: 2026-05-12T11:16:19.517
Modified: 2026-05-12T11:16:19.517
Link: CVE-2026-41713
No data.
OpenCVE Enrichment
Updated: 2026-05-12T12:30:15Z
Weaknesses