A Wolf in Sheep'S Clothing: Targeted Routing Hijacking in Federated RAG

Federated Retrieval-Augmented Generation FedRAG is attractive for privacy-sensitive applications because raw data remain local. As a result, routing must rely on client-provided semantic profiles, creating a new opportunity for manipulation. We introduce Routing Hijacking, a routing-stage attack ...

How AI Hallucinations Are Creating Real Security Risks

AI hallucinations are introducing serious security risks into critical infrastructure decision-making by exploiting human trust through highly confident yet incorrect outputs. When an AI model lacks certainty, it doesn’t have a mechanism to recognize that. Instead, it generates the most probable...

PT-2026-36667

CVE-2026-30412 SentinelCloud, AI-Driven Autonomous DevOps Engineer One closed loop. Five agents. Seven scenarios. Zero hallucinated kubectl. Live demo https://t.co/ocEWNzLf9Z...

An Empirical Security Evaluation of LLM-Generated Cryptographic Rust Code

Developers and organizations are using Large Language Models LLMs to generate security-critical code more frequently than ever, including cryptographic solutions for their products. This study presents an empirical evaluation of cryptographic security in 240 Rust code samples for two crypto...

Henry IV, Hotspur, Hal, and hallucinations

Welcome to this week's edition of the Threat Source newsletter. " 'Tis dangerous to take a cold, to sleep, to drink; but I tell you, my lord fool, out of this nettle, danger, we pluck this flower, safety." - Hotspur, Shakespeare's Henry IV, Part 1: Act 2 Scene 3 I get it. Hotspur is the...

HFuzzer: Testing Large Language Models for Package Hallucinations Via Phrase-Based Fuzzing

Large Language Models LLMs are widely used for code generation, but they face critical security risks when applied to practical production due to package hallucinations, in which LLMs recommend non-existent packages. These hallucinations can be exploited in software supply chain attacks, where...

Extending the OWASP Multi-Agentic System Threat Modeling Guide: Insights from Multi-Agent Security Research

We propose an extension to the OWASP Multi-Agentic System MAS Threat Modeling Guide, translating recent anticipatory research in multi-agent security MASEC into practical guidance for addressing challenges unique to large language model LLM-driven multi-agent architectures. Although OWASP's...

Diverging Towards Hallucination: Detection of Failures in Vision-Language Models Via Multi-Token Aggregation

Vision-language models VLMs now rival human performance on many multimodal tasks, yet they still hallucinate objects or generate unsafe text. Current hallucination detectors, e.g., single-token linear probing SLP and PTrue, typically analyze only the logit of the first generated token or just its...

New “Slopsquatting” Threat Emerges from AI-Generated Code Hallucinations

AI code tools often hallucinate fake packages, creating a new threat called slopsquatting that attackers can exploit in…...

The New York Times vs. OpenAI: A Turning Point for Web Scraping?

In a recent blog, we covered the blurry lines of legality surrounding web scraping and how the advent of artificial intelligence AI and large language models LLMs further complicates the matter. Shortly after publishing the blog, a significant legal development began unfolding: The New York Times...

A week in security (January 1 – January 7)

Last week on Malwarebytes Labs: Police investigate sexual assault on an avatar How AI hallucinations are making bug hunting harder Explained: SMTP smuggling Facebook introduces another way to track you – Link History 23andMe blames "negligent" breach victims, says it’s their own fault Microsoft...

How AI hallucinations are making bug hunting harder

Bug bounty programs that pay people for finding bugs are a very useful tool for improving the security of software. But with the availability of artificial intelligence AI as seen in the popular large language models LLMs like ChatGPT, Bard, and others it looks like there is a new problem on the...