CVE-2026-41713

highpriority · track · 0EPSS 0.002 · 12 %ileEUUS

grimoire priorityP2 · Scheduled

Exploitable?

—

no known exploitation

Likely / severe?

0.22% (12th) EPSS

CVSS 8.2 · high

Is it mine?

6 products

Check your exposure

Who says so?

4 sources

cnnvd · enisa_euvd · nvd · osv

EPSS · scored 2026-10-28

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.

cvss

Technical severity, 0–10. One row per scoring source.

8.2

010

base score 0–10 · higher = more severe · hover a vector to decode

v3.18.2highCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:Nsecondary · ENISA EU

v3.18.2highCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:Nsecondary · security@vmware.comexploitability 3.9 · impact 4.2

v3.18.2highCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:Nsecondary · OSV

v3.17.5highCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:N/E:Usecondary · CVSS-BT (t0sche)

ssvc

A stakeholder decision — act, attend, or track — from exploitation and impact.

Exploitation: none · Automatable: yes · Technical Impact: partialcoordinatorcisa_ssvcUS

weaknesses

The CWE weakness classes this flaw belongs to.

CWE-1336USCWE-1336US

affected products (6)

Products and version ranges known to be affected.

VMware Spring AI1.0.0 → 1.0.7enisa_euvdEU
VMware Spring AI1.1.0 → 1.1.6enisa_euvdEU
vmware spring ai1.0.0 → 1.0.7nvdUScpe:2.3:a:vmware:spring_ai:*:*:*:*:*:*:*:*
vmware spring ai1.1.0 → 1.1.6nvdUScpe:2.3:a:vmware:spring_ai:*:*:*:*:*:*:*:*
Maven org.springframework.ai:spring-ai-client-chat< 1.0.7osvUSpkg:maven/org.springframework.ai/spring-ai-client-chat
Maven org.springframework.ai:spring-ai-client-chat1.1.0-M1 → 1.1.6osvUSpkg:maven/org.springframework.ai/spring-ai-client-chat

advisories (1)

Vendor and ecosystem advisories describing this.

GHSA-5852-phmh-8fhrSpring AI: Prompt Injection via Memory Poisoning in PromptChatMemoryAdvisor2026-05-12ghsa · osvUS
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.

also known as (3)

Other names and identifiers for this entity.

sources

Which sources assert this record, and when.

cnnvd enisa_euvd nvd osv NVD CVE.org MITRE

published 2026-05-12modified 2026-10-26

references (6)

External citations — patches, advisories, analysis.

scry

Attackers weaponise vulnerabilities like this against internet-exposed services. See what is exposed on your perimeter with a free passive scan.

Free scan