Research reports
1,224 reports from 387 publishers45 added in the past week
10 reports, newest added first
Added Wed 14 Oct
WTF is AI poisoning?
This article is a WTF explainer, in which we break down media and marketing’s most confusing terms. More from the series → Marketers have been trying to game LLM responses to suit their brands since users began turning to AI for search. In recent months,…
AI
Threat Actors are Finding Their Way into Your AI Summaries
AI summaries have become ubiquitous in the modern search engine. They are often the first result that users see and helpfully contain links alongside their authoritatively worded answers. However, these answer engines are fallible, and their responses could…
AI
ClickFix Style Attack Uses Grok, ChatGPT for Malware Delivery
A new attack uses SEO poisoning and popular AI models to deliver infostealer malware, all while leveraging legitimate domains. ClickFix attacks have gained significant popularity over the past year, using otherwise benign CAPTCHA-style prompts to lure users…
MalwareAI
Attackers Target Agents via The Skill Supply Chain
An active malware campaign used typosquatted skills, trojanized packages, and remote loaders to target users of popular AI tools. TL;DR We disrupted an active malware campaign targeting agents through typosquatted skills. It targets users of popular AI tools…
MalwareSupply chainAI
Added Tue 6 Oct
JADEPUFFER evolves: The agentic threat actor deploys ransomware built to destroy AI models
Falco Feeds extends the power of Falco by giving open source-focused companies access to expert-written rules that are continuously updated as new threats are discovered. learn more Ransomware operators make a bet that their victims don’t keep backups. In a…
RansomwareAI
Added Tue 8 Sep
Prompts as Code & Embedded Keys
This is an abridged version of the LABScon 2025 presentation “LLM-Enabled Malware In the Wild” by the authors. A LABScon Replay video of the full talk will be released in due course. As Large Language Models (LLMs) are increasingly incorporated into…
MalwareAI
Added Tue 28 Jul
AI Security Incident Case: JadePuffer Ransomware Leverages AI Agent to Automate Attacks
In early July 2026, security firm Sysdig publicly disclosed a new type of ransomware attack. After gaining initial access by exploiting a Langflow vulnerability (CVE-2025-3248), the JadePuffer ransomware leveraged a Large Language Model (LLM) agent to…
RansomwareVulnerabilitiesAI
Added Thu 14 May
A Slopoly start to AI-enhanced ransomware attacks
In early 2026, IBM X-Force discovered a likely AI-generated novel malware which we are dubbing “Slopoly,” used during a ransomware attack. The operators are part of a group tracked as Hive0163, whose main objective is extortion through large-scale data…
RansomwareMalwareAI
Added Thu 23 Apr
In the Wild: Malware Prototype with Embedded Prompt Injection
In this write-up we present a malware sample found in the wild that boasts a novel and unusual evasion mechanism — an attempted prompt injection (”Ignore all previous instructions…”) aimed to manipulate AI models processing the sample. The sample gives the…
MalwareAI
Titles, excerpts and images come from each report or its publisher’s page, and every entry links to the publisher.