Trojans in Artificial Intelligence (TrojAI) Final Report

The Intelligence Advanced Research Projects Activity IARPA launched the TrojAI program to confront an emerging vulnerability in modern artificial intelligence: the threat of AI Trojans. These AI trojans are malicious, hidden backdoors intentionally embedded within an AI model that can cause a...

Malicious code in tailwindcss-animation-modern (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 1c6fbd472c63dae399a454decb6c6c097b7ae23766e0962ec081f0ad685ea451 The package tailwindcss-animation-modern was found to contain malicious code. Source: ghsa-malware...

Microsoft Develops Scanner to Detect Backdoors in Open-Weight Large Language Models

Microsoft on Wednesday said it built a lightweight scanner that it said can detect backdoors in open-weight large language models LLMs and improve the overall trust in artificial intelligence AI systems. The tech giant's AI Security team said the scanner leverages three observable signals that ca...

The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers

Detecting whether a model has been poisoned is a longstanding problem in AI security. In this work, we present a practical scanner for identifying sleeper agent-style backdoors in causal language models. Our approach relies on two key findings: first, sleeper agents tend to memorize poisoning dat...

Hardware-Triggered Backdoors

Machine learning models are routinely deployed on a wide range of computing hardware. Although such hardware is typically expected to produce identical results, differences in its design can lead to small numerical variations during inference. In this work, we show that these variations can be...

MAL-2026-587 Malicious code in chai-px (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector cfeac68ac3a89859c0a6c38e5d55e4e2e9b9ffa77476a10cdc1d31de070bea68 The package chai-px was found to contain malicious code. Source: ghsa-malware 708ec6326dbafd483773c64035513b5cd8be0a0842c3d44d92af9eee01408b8a Any...

MAL-2026-535 Malicious code in knex.js (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 04fcb32607ead73fe3f1c4443e807ae1deec8bda92999d19da73075af9d61805 The package knex.js was found to contain malicious code. Source: ghsa-malware a1c9b559496940535edc51721d08a3fccda2739e33e34028d59d97b305452aba Any...

PeckBirdy: A Versatile Script Framework for LOLBins Exploitation Used by China-aligned Threat Groups

PeckBirdy is a sophisticated JScript-based C&C framework used by China-aligned APT groups to exploit LOLBins across multiple environments, delivering advanced backdoors to target gambling industries and Asian government entities...

CVE-2026-1331

MeetingHub developed by HAMASTAR Technology has an Arbitrary File Upload vulnerability, allowing unauthenticated remote attackers to upload and execute web shell backdoors, thereby enabling arbitrary code execution on the server...

CVE-2026-0933

SummaryA command injection vulnerability CWE-78 has been found to exist in the wrangler pages deploy command. The issue occurs because the --commit-hash parameter is passed directly to a shell command without proper validation or sanitization, allowing an attacker with control of --commit-hash to...

Malicious code in theme-neutral (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector b9701381076541b8fbe448e03eb174cb40e2fd27237bfb442f219bf94911d035 The package theme-neutral was found to contain malicious code. Source: ghsa-malware 50a19fb9e329c206942de6cdd79f346a105320f4e71d0b652b154001b1dde8e7...

PT-2026-3542

Name of the Vulnerable Software and Affected Versions PrismX MX100 AP controller affected versions not specified Description The PrismX MX100 AP controller developed by BROWAN COMMUNICATIONS has an arbitrary file upload issue. This allows remote attackers with sufficient privileges to upload and...

A week in security (January 12 – January 18)

Last week on Malwarebytes Labs: WhisperPair exposes Bluetooth earbuds and headphones to tracking and eavesdropping Dutch police sell fake tickets to show how easily scams work "Reprompt" attack lets attackers steal data from Microsoft Copilot Phishing scammers are posting fake "account restricted...

Malicious code in ofjaaah-security-lib (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 94bfbd5c89af01468786a4ff45da3126dbd49e28e4a250d0d124fc65b1f0c508 The package ofjaaah-security-lib was found to contain malicious code. Source: ghsa-malware...

Exploit for CVE-2025-8489

100-days-challenge-day-21--WP scan WP Scan helped identify co...

Corrupting LLMs Through Weird Generalizations

Fascinating research: Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs. Abstract LLMs are useful because they generalize so well. But can you have too much of a good thing? We show that a small amount of finetuning in narrow contexts can dramatically shift behavior outside...

CVE-2022-0687

The Amelia WordPress plugin before 1.0.47 stores image blobs into actual files whose extension is controlled by the user, which may lead to PHP backdoors being uploaded onto the site. This vulnerability can be exploited by logged-in users with the custom "Amelia Manager" role...

Fake WinRAR downloads hide malware behind a real installer

A member of our web research team pointed me to a fake WinRAR installer that was linked from various Chinese websites. When these links start to show up, that’s usually a good indicator of a new campaign. So, I downloaded the file and started an analysis, which turned out to be something of a...

CVE-2025-15240

QOCA aim AI Medical Cloud Platform developed by Quanta Computer has an Arbitrary File Upload vulnerability, allowing authenticated remote attackers to upload and execute web shell backdoors, thereby enabling arbitrary code execution on the server...

CVE-2025-15240

QOCA aim AI Medical Cloud Platform developed by Quanta Computer has an Arbitrary File Upload vulnerability, allowing authenticated remote attackers to upload and execute web shell backdoors, thereby enabling arbitrary code execution on the server...