Prompt Injection via Memory Poisoning in PromptChatMemoryAdvisor

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.

Scores

EPSS (exploitation in 30 days)

0.22% · top 88% of all CVEs (6 Nov 2026)

CISA SSVC

Exploitation: none · Automatable: yes · Technical impact: partial

The list uses the assigner's score when there is one, then CISA's, then NVD's: High 8.2.

Weakness

• CWE-1336 Improper Neutralization of Special Elements Used in a Template Engine (opens in a new tab)All about CWE-1336 and its CVEs

Affected products

• VMware · Spring AI

  • affected 1.0.0 – < 1.0.7
  • affected 1.1.0 – < 1.1.6

Affected packages

From reviewed advisories of the GitHub Advisory Database.

• Mavenorg.springframework.ai:spring-ai-client-chatGHSA-5852-phmh-8fhr (opens in a new tab)

References (2)

• https://spring.io/security/cve-2026-41713 (opens in a new tab)
• https://nvd.nist.gov/vuln-metrics/cvss/v3-calculator?vector=AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:N&version=3.1 (opens in a new tab)

Sources

The same CVE in the primary databases and aggregators, to check against.

• CVE.org record (opens in a new tab)
• CVE List JSON (GitHub) (opens in a new tab)
• NVD (opens in a new tab)
• FIRST EPSS (opens in a new tab)
• OSV.dev (opens in a new tab)
• GitHub Advisory GHSA-5852-phmh-8fhr (opens in a new tab)
• CIRCL Vulnerability-Lookup (opens in a new tab)

Badge for a README or a ticket

[![CVE-2026-41713](https://trackcve.app/badge/CVE-2026-41713.svg)](https://trackcve.app/cve/CVE-2026-41713)

Record last updated 12 May 2026, 12:11 UTC.