NIST deprecates RSA-2048 from 2030. Find every one of them before attackers do.
☕
☕ Maven
Not in CISA KEV
HIGH severity

Spring AI: Prompt Injection via Memory Poisoning in PromptChatMemoryAdvisorGHSA-5852-phmh-8fhr

HIGH

GHSA-5852-phmh-8fhr is a high-severity (CVSS 8.2) CWE-1336 vulnerability in org.springframework.ai:spring-ai-client-chat. A fix is available for org.springframework.ai:spring-ai-client-chat — see the affected versions and patch details below.

Also known asCVE-2026-41713
Published
Updated
Affected
2 pkgs
Patched
2 / 2
Exploits
None indexed
Exploitation data as of Nov 10, 2026 · OSV.dev, NVD, FIRST.org (EPSS)

Exploitation Status

No confirmed exploitation observed yet

  • CISA assesses this as automatable — exploitation doesn’t require manual, per-target effort, which raises the odds of mass scanning and opportunistic attacks.
  • CISA’s own triage has not observed active exploitation or public proof-of-concept code for this CVE as of its last assessment.

Exploitation and automatability from CISA’s SSVC triage for GHSA-5852-phmh-8fhr.

EPSS Exploitation Probability

via FIRST.org ↗
0.2%probability of exploitation in next 30 days
Lower Risk0.00%
Lower risk than most CVEs12th percentile — riskier than 12% of all scored CVEsHighest risk
0.00%0.24%0.48%0.72%0.2%0.2%Jul 26Nov 26

Probability of exploitation in the next 30 days, from FIRST.org EPSS.

How urgent is this, really

Where this sits among everything scored

Real-World Exposure

2 pkgs affected
☕org.springframework.ai:spring-ai-client-chat☕org.springframework.ai:spring-ai-client-chat

Real-time download stats are indexed for npm and PyPI packages. This vulnerability affects Maven packages — download data is not available via public APIs for these ecosystems.

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.

Affected Packages

2 total 2 fixed
EcosystemPackageVulnerable rangeFix
☕Mavenorg.springframework.ai:spring-ai-client-chatall versions1.0.7org.springframework.ai:spring-ai-client-chat:1.0.7
☕Mavenorg.springframework.ai:spring-ai-client-chat≥ 1.1.0-M1&&< 1.1.61.1.6org.springframework.ai:spring-ai-client-chat:1.1.6

Affected Products

1 product · 2 configurations
Application
spring aivmware
≥ 1.1.0 && < 1.1.6
range

Detection & mitigation playbook

Open-source dependency

  1. Detect

    Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for org.springframework.ai:spring-ai-client-chat, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.

  2. Fix

    Update org.springframework.ai:spring-ai-client-chat to 1.0.7 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-5852-phmh-8fhr is resolved across your whole dependency graph.

  3. Workarounds

    If you can't upgrade right away: gate or disable the affected feature, validate untrusted input at the boundary, and avoid passing attacker-controlled data into the vulnerable path. O3's runtime protection blocks exploitation in production as an interim safeguard until the upgrade lands.

Frequently Asked Questions

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.
O3 Security · Impact-Aware SCA

Is GHSA-5852-phmh-8fhr in your dependencies?

Find it across Maven, including transitive dependencies.

Scan my dependencies How O3 SCA works
Spring AI: Prompt Injection via Memory Poisoning in…