CVE-2026-41713: Prompt Injection via Memory Poisoning in PromptChatMemoryAdvisor
VMware · Spring AI
Vendor fix available · Affected: VMware Spring AI · Exploitation: unlikely (under 1%)
Not in CyberSIXT coverage yet: no article names this CVE. This page shows the public record.
Higher than 12% of scored CVEs
DescriptionCVE.org
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 products1
From the CVE record. A product or version that is not listed is unknown, not unaffected.
- VMware · Spring AIfrom 1.0.0 before 1.0.7; from 1.1.0 before 1.1.6
On the Atlas
Every published CVE is on the CyberSIXT Atlas, grouped by weakness, vendor and month.
- Exploitation
- Unlikely (under 1%). EPSS under 1%, or no score yet.
- CISA KEV
- Not listed
- Public check
- No public nuclei template
- Weakness
- Improper Neutralization of Special Elements Used in a Template Engine · Command and Code Injection
- Vendor
- VMware
- Published
- May 2026
CoverageNo articles yet
No CyberSIXT article names CVE-2026-41713 yet, so there is no coverage timeline, action brief or change log for it. Everything on this page comes from the public CVE record, CISA KEV, EPSS and the nuclei template index. Search the archive or see the CVEs in the news.