MAL-2026-3615 Malicious code in ai-spellcheckers (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: kam193 205425d7a8407b8bed958a99660e2ec74e21f9b0e1427659529636347333c5c9 Packages contain hidden code that is effectively run during importing or using the library, and downloads second stage code. Then, a process running in...

CVE-2025-36515

Uncontrolled search path for some AI Playground software before version 3.0.0 alpha within Ring 3: User Applications may allow an escalation of privilege. Unprivileged software adversary with an authenticated user combined with a high complexity attack may enable escalation of privilege. This...

Pwn2Own Berlin 2026 Hits Capacity as Rejected Hackers Release 0-Days

Pwn2Own Berlin 2026 reportedly reached full capacity for the first time, prompting rejected researchers to publicly disclose zero-day exploits targeting Firefox, NVIDIA, and AI platforms...

CVE-2025-36515

CVE-2025-36515 affects AI Playground software prior to 3.0.0 alpha. The issue is an Uncontrolled search path vulnerability in Ring 3: User Applications that can lead to privilege escalation. An unprivileged adversary with an authenticated user and high attack complexity could exploit a local atta...

CVE-2025-36515

Uncontrolled search path for some AI Playground software before version 3.0.0 alpha within Ring 3: User Applications may allow an escalation of privilege. Unprivileged software adversary with an authenticated user combined with a high complexity attack may enable escalation of privilege. This...

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...

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...

Mini Shai-Hulud Worm Compromises TanStack, Mistral AI, Guardrails AI & More Packages

TeamPCP , the threat actor behind the recentsupply chain attack spree, has been linked to the compromise of the npm and PyPI packages from TanStack, UiPath, Mistral AI, OpenSearch, and Guardrails AI as part of a fresh Mini Shai-Hulud campaign. The affected npm packages have been modified to inclu...

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...

Malicious code in @dirigible-ai/sdk (npm)

--- -= Per source details. Do not edit below this line.=- Source: google-open-source-security 5e1924464368f0c5816ee84e000cc47017f44045140feafbbc9e685d847ed5a5 This package was compromised as part of the "Mini Shai-Hulud is back" worm by the TeamPCP threat actor. The package will steal credentials...

Malicious code in guardrails-ai (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: google-open-source-security 5e1924464368f0c5816ee84e000cc47017f44045140feafbbc9e685d847ed5a5 This package was compromised as part of the "Mini Shai-Hulud is back" worm by the TeamPCP threat actor. The package will steal credentials...

MAL-2026-3593 Malicious code in @dirigible-ai/sdk (npm)

--- -= Per source details. Do not edit below this line.=- Source: google-open-source-security 5e1924464368f0c5816ee84e000cc47017f44045140feafbbc9e685d847ed5a5 This package was compromised as part of the "Mini Shai-Hulud is back" worm by the TeamPCP threat actor. The package will steal credentials...

MAL-2026-3607 Malicious code in guardrails-ai (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: google-open-source-security 5e1924464368f0c5816ee84e000cc47017f44045140feafbbc9e685d847ed5a5 This package was compromised as part of the "Mini Shai-Hulud is back" worm by the TeamPCP threat actor. The package will steal credentials...

Exploit for CVE-2024-12912

Origasus origasus.go ile derlenen, ASUS AiCloud / AsusWRT i...

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...

JunoClaw 输入验证错误漏洞

JunoClaw is a decentralized AI proxy platform developed by Dragonmonk111. Versions prior to JunoClaw 0.x.y-security-1 contained a vulnerability related to input validation errors. This vulnerability stemmed from the uploadwasm MCP tool accepting file system paths provided by the proxy without...

Intel AI Playground 代码问题漏洞

Intel AI Playground is an online platform operated by Intel Corporation in the United States. Previous versions of Intel AI Playground, including 3.0.0 alpha, had code vulnerabilities that stemmed from uncontrolled search paths, which could lead to privilege escalation...

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...

CVE-2026-31233

CVE-2026-31233 affects Guardrails AI through version 0.6.7. The vulnerability resides in the Hub package installation mechanism: when installing validator packages, the system fetches a manifest from the Guardrails Hub and dynamically executes a script specified in the post_install field. The scr...