CVE-2026-41863 LLM-influenced filename used unsanitized in Path.resolve before file write in Spring AI support for Anthropic Skills API

Spring AI's support for Anthropic's Skills API used LLM-influenced filenames unsanitized in Path.resolve before writing files to disk. This could allow a malicious user to write files outside the intended target directory, including restricted directories. Affected versions: Spring AI: 1.1.0...

CVE-2026-41863 LLM-influenced filename used unsanitized in Path.resolve before file write in Spring AI support for Anthropic Skills API

Spring AI's support for Anthropic's Skills API used LLM-influenced filenames unsanitized in Path.resolve before writing files to disk. This could allow a malicious user to write files outside the intended target directory, including restricted directories. Affected versions: Spring AI: 1.1.0...

EUVD-2026-31638

Spring AI's support for Anthropic's Skills API used LLM-influenced filenames unsanitized in Path.resolve before writing files to disk. This could allow a malicious user to write files outside the intended target directory, including restricted directories. Affected versions: Spring AI: 1.1.0...

PT-2026-43006

Name of the Vulnerable Software and Affected Versions Spring AI versions 1.1.0 through 1.1.x Description Support for Anthropic's Skills API uses filenames influenced by the Large Language Model LLM without proper sanitization in the Path.resolve function before writing files to disk. This flaw...

VMware Spring AI 安全漏洞

VMware Spring AI is a development framework from VMware that integrates Artificial Intelligence and Large Language Modeling capabilities in the Spring ecosystem. A security vulnerability exists in VMware Spring AI versions 1.1.0 through 1.1.x. The vulnerability stems from a failure to clean up...

This Week in Spring - May 19th, 2026

Hi Spring fans! Welcome to another installment of This Week in Spring!, this one written from the back of a taxi racing to the local Frankfurt train station, where I'll take a train to Munich for the amazing Kotlin Conf 2026 edition, where I'll be part of the keynote and deliver a talk on the...

GHSA-5852-PHMH-8FHR Spring AI: Prompt Injection via Memory Poisoning in PromptChatMemoryAdvisor

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...

GHSA-Q62F-H9X2-GCQC Spring AI: ChatMemory DEFAULT_CONVERSATION_ID causes unintended cross-user data leakage

Spring AI's chat memory component contained a problematic default that, when not explicitly overridden, could result in unintended data exposure between users...

CVE-2026-41712

Spring AI's chat memory component contained a problematic default that, when not explicitly overridden, could result in unintended data exposure between users...

CVE-2026-41712

Spring AI's chat memory component contained a problematic default that, when not explicitly overridden, could result in unintended data exposure between users...

PT-2026-40006

Spring AI's chat memory component contained a problematic default that, when not explicitly overridden, could result in unintended data exposure between users...

VMware Spring AI 安全漏洞

VMware Spring AI is a development framework by the American company VMware, which integrates artificial intelligence and large language model capabilities into the Spring ecosystem. VMware Spring AI has a security vulnerability, which stems from problematic default settings in the chat memory...

VMware Spring AI 安全漏洞

VMware Spring AI is a development framework created by VMware Corporation in the Spring ecosystem, which integrates artificial intelligence and large language model capabilities. VMware Spring AI has a security vulnerability. This vulnerability allows malicious users to manipulate the behavior of...

GHSA-V632-2M87-7469 Spring AI's MilvusVectorStore#doDelete(List) implementation is vulnerable to filter-expression injection via unsanitized document IDs

Spring AI's MilvusVectorStoredoDeleteList implementation is vulnerable to filter-expression injection via unsanitized document IDs. Spring AI 1.0.x: affected from 1.0.0 through latest 1.0.x; upgrade to 1.0.7 or greater. Spring AI 1.1.x: affected from 1.1.0 through latest 1.1.x; upgrade to 1.1.6 o...

Spring AI's MilvusVectorStore#doDelete(List) implementation is vulnerable to filter-expression injection via unsanitized document IDs

Spring AI's MilvusVectorStoredoDeleteList implementation is vulnerable to filter-expression injection via unsanitized document IDs. Spring AI 1.0.x: affected from 1.0.0 through latest 1.0.x; upgrade to 1.0.7 or greater. Spring AI 1.1.x: affected from 1.1.0 through latest 1.1.x; upgrade to 1.1.6 o...

CVE-2026-41705

Spring AI's MilvusVectorStoredoDeleteList implementation is vulnerable to filter-expression injection via unsanitized document IDs. Spring AI 1.0.x: affected from 1.0.0 through latest 1.0.x; upgrade to 1.0.7 or greater. Spring AI 1.1.x: affected from 1.1.0 through latest 1.1.x; upgrade to 1.1.6 o...

CVE-2026-41705

The CVE affects Spring AI MilvusVectorStore#doDelete(List) and is caused by a filter-expression injection from unsanitized document IDs. Affected are Spring AI 1.0.x (1.0.0–1.0.x); upgrade to 1.0.7+; and Spring AI 1.1.x (1.1.0–1.1.x); upgrade to 1.1.6+. CVSSv3.1 base score 8.6 (HIGH): Network acc...

PT-2026-39225

Name of the Vulnerable Software and Affected Versions Spring AI versions 1.0.0 through 1.0.6 Spring AI versions 1.1.0 through 1.1.5 Description The doDeleteList function in the MilvusVectorStore implementation is susceptible to filter-expression injection. This occurs because document IDs are not...

Prompt Injection

Overview org.springframework.ai:spring-ai-model is a Core model interfaces and classes for Spring AI Affected versions of this package are vulnerable to Prompt Injection via conversation memory handling in the affected advisor. An attacker can inject crafted input in conversation memory that is...

SQL Injection

org.springframework.ai, spring-ai-azure-cosmos-db-store is vulnerable to SQL Injection. The vulnerability is due to improper handling of crafted document IDs in the CosmosDBVectorStore, which allows an attacker to execute arbitrary SQL queries...