CVE-2026-41713 Prompt Injection via Memory Poisoning in PromptChatMemoryAdvisor

High 8.2 Published Updated

Attackers can manipulate AI model behavior via prompt injection in Spring AI's memory advisor, requiring library upgrades.

Exploited in the wild
Not known
Login needed
Not needed
Attackable
Over the internet
Victim action needed
Not needed
Fix
Available

What is CVE-2026-41713?

CVE-2026-41713 is a high-severity vulnerability in VMware Spring AI, published on 12 May 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.

Official 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.

Weakness: CWE-1336

Which versions are affected by CVE-2026-41713?

4 open source packages ship an affected version, including org.springframework.ai:spring-ai-client-chat. It affects 1 product.

PackageAffectedFixed in
org.springframework.ai:spring-ai-client-chat MavenAll versions1.0.7
org.springframework.ai:spring-ai-client-chat MavenAll versions1.0.7
org.springframework.ai:spring-ai-client-chat MavenFrom 1.1.0-M11.1.6
org.springframework.ai:spring-ai-client-chat MavenFrom 1.1.0-M11.1.6

Products include Vmware Spring Ai.

How do I fix CVE-2026-41713?

Upgrade org.springframework.ai:spring-ai-client-chat to a fixed version for your release line: 1.0.7 or 1.1.6.

Is CVE-2026-41713 being exploited?

There is no known exploitation of CVE-2026-41713 in the wild and no public exploit code.

Sources

Also known as GHSA-5852-phmh-8fhr, MINI-3ff7-m467-fmmg, MINI-8rr9-h8jr-6jc2.

Is CVE-2026-41713 in your software?

Upload an SBOM and sbomify checks it against every vulnerability here, every day.

Check your SBOMs for free