CVE-2026-41713

published 12 May 2026 · updated 12 May 2026

Prompt Injection via Memory Poisoning in PromptChatMemoryAdvisor

8.2HighCVSS 8.2EPSS 0%

No exploitation in the wild has been reported. EPSS puts the chance of exploitation in the next 30 days at 0%. Fixed in Spring AI 1.0.7 and Spring AI 1.1.6.

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

Vendors, products and packages with version ranges

VendorProductVersionsFixed
VMwareSpring AI>=1.0.0 <1.0.7, >=1.1.0 <1.1.61.0.7, 1.1.6

Timeline

Every event on this vulnerability

Related

Other vulnerabilities in VMware, strongest first

Embed

A live severity badge for an advisory, README or ticket

CVE-2026-41713 severity on Zeptric[![CVE-2026-41713](https://zeptric.io/badge/cve/CVE-2026-41713.svg)](https://zeptric.io/cve/CVE-2026-41713)