Read the docs
TI-2026-30229 Aliases CVE-2026-41713GHSA-5852-phmh-8fhr

Prompt Injection via Memory Poisoning in PromptChatMemoryAdvisor

Priority MEDIUM 41CWE-1336Published · Updated

Key facts

Attack vector
Network
Privileges required
None
User interaction
None
Attack complexity
Low
Impact type
Code execution
Confidentiality · integrity · availability
Low · High · None
Fix status
Fixed

Attack profile from CVSS 3.1 · CNA. Fix status from CNA and GitHub. Impact type from CWE-1336.

Summary

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.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV
EPSS 0.00218 12th percentileScored 2026-11-07
Fix Fixed Spring AI (VMware): 1.0.7, 1.1.6org.springframework.ai:spring-ai-client-chat (Maven): 1.0.7, 1.1.6

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
None
Automatable
Yes
Technical impact
Partial

The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.

Affected products

VendorProductAffected versionsFixed inStatusSource
VMwareSpring AI1.0.0 to before 1.0.7; 1.1.0 to before 1.1.61.0.7, 1.1.6Patch availableCNA
—org.springframework.ai:spring-ai-client-chat (Maven)before 1.0.71.0.7Patch availableGHSA-5852-phmh-8fhr
—org.springframework.ai:spring-ai-client-chat (Maven)1.1.0-M1 to before 1.1.61.1.6Patch availableGHSA-5852-phmh-8fhr
  • Spring AI VendorVMware Affected 1.0.0 to before 1.0.7; 1.1.0 to before 1.1.6 Fixed in 1.0.7, 1.1.6 Patch available CNA
  • org.springframework.ai:spring-ai-client-chat (Maven) Vendor— Affected before 1.0.7 Fixed in 1.0.7 Patch available GHSA-5852-phmh-8fhr
  • org.springframework.ai:spring-ai-client-chat (Maven) Vendor— Affected 1.1.0-M1 to before 1.1.6 Fixed in 1.1.6 Patch available GHSA-5852-phmh-8fhr

CPE configurations NVD · 1

CPEVersionsRoleVendor
cpe:2.3:a:vmware:spring_ai:*:*:*:*:*:*:*:*1.0.0 to before 1.0.7; 1.1.0 to before 1.1.6VulnerableVMware
  • cpe:2.3:a:vmware:spring_ai:*:*:*:*:*:*:*:* Versions 1.0.0 to before 1.0.7; 1.1.0 to before 1.1.6 Vulnerable ·VMware

Remediation

  • Fix · CNA Spring AI (VMware) Fixed in 1.0.7, 1.1.6
  • Fix · GHSA-5852-phmh-8fhr org.springframework.ai:spring-ai-client-chat (Maven) Fixed in 1.0.7 Advisory →
  • Fix · GHSA-5852-phmh-8fhr org.springframework.ai:spring-ai-client-chat (Maven) Fixed in 1.1.6 Advisory →

Fixed in the same release

Records fixed by the same vendor advisory or release, as the CNA lists them.

  • Release ·

    VMware Spring AI 1.0.7, 1.1.6

    2 records Highest priority Priority MEDIUM 1 MEDIUM, 1 LOW

    Other records, highest priority first

    • TI-2026-30228 ChatMemory DEFAULT_CONVERSATION_ID causes unintended cross-user data leakagePriority LOW 38

Timeline

  1. 2026-10-02 Threatist record created from CVE-2026-41713
  2. 2026-10-03 Alias added: GHSA-5852-phmh-8fhr

References

  • TI-2026-18262 SpEL Injection via Unescaped Filter Key in SimpleVectorStore Leads to Remote Code Execution CVSS 3.1CRITICAL 9.8
  • TI-2026-29618 Code injection in VMware Spring AI CVSS 3.1HIGH 8.6
  • TI-2026-18254 CVE-2026-22729: JSONPath Injection in Spring AI Vector Stores FilterExpressionConverter CVSS 3.1HIGH 8.6
  • TI-2026-35287 Spring AI vector store metadata filtering to handle special characters in Elasticsearch… CVSS 3.1HIGH 8.6
  • TI-2026-30221 Expression language injection in VMware Spring AI CVSS 3.1HIGH 8.6
  • TI-2026-18266 Server-Side Request Forgery in BedrockProxyChatModel via Unvalidated Media URL Fetching CVSS 3.1HIGH 8.6
See all 22 →

Sources