VMware Advisor Input Injection Alters Model Behavior
CVE-2026-41713 Published on May 12, 2026
Prompt Injection via Memory Poisoning in PromptChatMemoryAdvisor
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.
Vulnerability Analysis
CVE-2026-41713 can be exploited with network access, and does not require authorization privileges or user interaction. This vulnerability is considered to have a low attack complexity. The potential impact of an exploit of this vulnerability is considered to have a small impact on confidentiality, a high impact on integrity, and no impact on availability.
Weakness Type
Products Associated with CVE-2026-41713
Want to know whenever a new CVE is published for VMware Spring Framework? stack.watch will email you.
Affected Versions
VMware Spring AI:- Version 1.0.0 and below 1.0.7 is affected.
- Version 1.1.0 and below 1.1.6 is affected.