CVE-2026-41713GHSA-5852-PHMH-8FHR
Prompt Injection via Memory Poisoning in PromptChatMemoryAdvisor
- Published
- Last modified
- Where the record stands: published, rejected by its publisher, or superseded by another id.What do these mean? →
- published
- Whether CISA lists it in its Known Exploited Vulnerabilities catalog: proof that attackers are using it.What do these mean? →
- Not listed in CISA KEV
- Fix
- Fixed in 1.0.7, 1.1.6
- Whether working attack code is public (Exploit-DB, Metasploit, Nuclei or GitHub). Public code makes attacks easier.What do these mean? →
- None on Exploit-DB, Metasploit or GitHub
CISA's decision points: whether it is exploited, whether attacks can be automated, and how much control an attacker gets. Assessed (SSVC 2.0.3).What do these mean? →
- Exploitation: none
- Automatable: yes
- Technical impact: partial
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.
Timeline
- CVE published
- CISA SSVC assessment
Exploitation: none · Automatable: yes · Technical impact: partial
- Record last updated
Affected versions
- VMware Spring AI
From 1.0.0 · fixed in 1.0.7; From 1.1.0 · fixed in 1.1.6
- org.springframework.ai:spring-ai-client-chatMaven
fixed in 1.0.7
- org.springframework.ai:spring-ai-client-chatMaven
From 1.1.0-M1 · fixed in 1.1.6