Cloud-based malware analysis service. Take your information security to the next level. Analyze suspicious and malicious activities using our innovative tools.
NetworkChuck Cloud Browser
The ultimate tool for threat research, open-source intelligence (OSINT) collections or accessing those high-risk links. Keep your online activities private and your devices safe from malware.
A New Tool Found Malware That’s Guided by an AI Hive Mind—No Humans in Sight
Cisco Talos researchers created a new framework for identifying malware and hacking tools that rely on AI chatbots—and quickly discovered something unusual.
From LinkedIn to Tailored Attack in 30 Minutes: How AI Accelerates Target Profiling for Cybercrime | TrendAI (US)
The industrialization of AI-driven OSINT has transformed individual digital footprints into machine-readable intelligence at scale, enabling attackers to operationalize personalized reconnaissance at volume.
Sprites - Stateful sandboxes
Persistent, hardware-isolated execution environments for arbitrary code. Run AI agents, untrusted code, and more in secure sandbox environments with checkpoint & restore.
Exposing AdFection: How Discover-Tech Turned Targeted Ads Into a Pipeline for Zero-Click Mercenary Spyware - The Citizen Lab
This is the first-ever public confirmation of zero-click mercenary spyware delivered via targeted ads. We call the technique AdFection, and show how it was used to infect devices at Al Jazeera with Candiru’s spyware. We also uncover Discover-Tech, and show how the company helps mercenary surveillance vendors track and hack devices around the world.
Never-before-seen Linux malware is “far more advanced than typical”
VoidLink includes an unusually broad and advanced array of capabilities.
Potential uses for the Privacy Sandbox
Today on The Keyword, we outlined our vision for an initiative aimed at evolving the web with architecture that advances privacy, while co...
Is sandboxing sufficient to contain rogue agents?
Quick caveats: this is a post on AI safety, written by a cryptography professor. If that troubles you, you should read something else. I try hard not to work on AI (except when the topic occasional…
Stop Clicking on Junk: How to Identify and Ignore AI-Generated Slop Today
The internet is slowly being flooded by AI slop. What is it and how can you avoid it?
The Malicious Use of Artificial Intelligence: Forecasting,...
This report surveys the landscape of potential security threats from malicious uses of AI, and proposes ways to better forecast, prevent, and mitigate these threats. After analyzing the ways in...
AI Agents Enable Adaptive Computer Worms
A computer worm is malware that spreads on a network by replicating itself from one machine to another. Traditional worms, like WannaCry, exploited predetermined vulnerabilities, and their spread can be halted by patching those vulnerabilities. Here we show that artificial intelligence (AI) agents enable a fundamentally new threat: a worm that generates tailored attack strategies to each target it encounters. The worm parasitically uses compromised machines to run open-weight large language models (LLMs) to sustain its reasoning, or extend its reach for further attacks. Deployed on a network of machines spanning Linux, Windows, and IoT (Internet of Things) devices, the worm propagated by exploiting common, real-world corporate network vulnerabilities. Since the worm is powered by stolen compute, the attacker's marginal cost per new infection is zero. This creates a destabilizing economic asymmetry between attackers and defenders. Moreover, because the worm requires no commercial AI platform, centralized safety controls, such as service refusals or rate limiting, are structurally irrelevant. Our results demonstrate that self-sustaining AI-driven cyber-threats are no longer theoretical. We must prepare for autonomous generative adversaries: malware systems that propagate without human operators and are defined not by fixed exploit code, but by the capacity to reason about targets, adapt to observations, and synthesize attack logic in real time.
AI-powered cyberattacks on websites surge
Artificial intelligence is thought to have made it easier for attackers to identify weaknesses in individual websites.
anthropic-experimental/sandbox-runtime
A lightweight sandboxing tool for enforcing filesystem and network restrictions on arbitrary processes at the OS level, without requiring a container.
Quantifying Frontier LLM Capabilities for Container Sandbox Escape
AI agents are demonstrating rapid improvement in capabilities: the length of some tasks that frontier models can complete autonomously—measured in human-equivalent time—has been doubling approximately every seven months (METR, 2025; AI Security Institute, 2025a). In cybersecurity, current models achieve non-trivial success (Zhang et al., 2025) on professional-level Capture the Flag challenges, and recent evaluations report 13% success rates on exploiting real-world web application vulnerabilities (Zhu et al., 2025b). These results indicate that modern models can already perform multi-step vulnerability discovery and exploitation.
Snowflake Cortex AI Escapes Sandbox and Executes Malware
PromptArmor report on a prompt injection attack chain in Snowflake's Cortex Agent, now fixed. The attack started when a Cortex user asked the agent to review a GitHub repository that …