Latest cybersecurity reporting from selected sources.

Security firm Sysdig says it has found what it believes is the first ransomware attack run from start to finish by an AI agent

LayerX tricked AI browsers including ChatGPT Atlas and Comet into bypassing their guardrails

Microsoft researchers have detailed an exploit chain, named AutoJack, that turns an AI browsing agent into a delivery vehicle for remote code execution

It's been one of those weeks. You expect the usual noise: recycled malware, sloppy attacks, another easy target getting hit. Instead, there's a supply chain attack kit in a public repo, a $5,000-a-month RAT that clones browsers, and research showing AI agents can be tricked into leaking real credentials

In February 2026, researchers uncovered a shift that completely changed the game: threat actors are now using custom AI setups to automate attacks directly into the kill chain

On January 31, 2026, researchers disclosed that Moltbook, a social network built for AI agents, had left its database wide open, exposing 35,000 email addresses and 1.5 million agent API tokens across 770,000 active agents

AI Dependency Attack Reportedly Exposes Data and Source CodeA LiteLLM supply-chain compromise enabled attackers to harvest credentials and access internal environments at scale at Mercor. The firm was the first to confirm a LiteLLM breach, and researchers are warning about growing AI system exposure and limited visibility.

The massive amount of junk code that hides the malware's logic from security scans was almost certainly generated by AI, researchers say.

DeepLoad logs keystrokes, buries details behind reams of AI-generated code, and re-infect hosts days after being blocked, according to ReliaQuest.  The post Researchers say credential-stealing campaign used AI to build evasion ‘at every stage’ appeared first on CyberScoop.

A new campaign has leveraged the ClickFix social engineering tactic as a way to distribute a previously undocumented malware loader referred to as DeepLoad

Researchers at ReliaQuest warn of persistent malware campaign targeting enterprise credentials

Cybersecurity researchers have uncovered a new set of malicious npm packages that are designed to steal cryptocurrency wallets and sensitive data

Bug Allows Attackers to Hijack AI Agents Via Poisoned DocumentationSecurity researchers at Noma Labs found a critical flaw in Context7, a widely used tool that feeds AI coding assistants documentation, allowing attackers to plant hidden instructions to steal credentials and delete files without touching a developer's machine.

Cybersecurity researchers have discovered a malicious npm package that masquerades as an OpenClaw installer to deploy a remote access trojan (RAT) and steal sensitive data from compromised hosts

Cybersecurity researchers have disclosed multiple security vulnerabilities in Anthropic's Claude Code, an artificial intelligence (AI)-powered coding assistant, that could result in remote code execution and theft of API credentials

Cybersecurity researchers have disclosed what they say is an active "Shai-Hulud-like" supply chain worm campaign that has leveraged a cluster of at least 19 malicious npm packages to enable credential harvesting and cryptocurrency key theft

Cybersecurity researchers disclosed they have detected a case of an information stealer infection successfully exfiltrating a victim's OpenClaw (formerly Clawdbot and Moltbot) configuration environment

Security researchers are warning of insecure deployments in enterprise environments of the Moltbot (formerly Clawdbot) AI assistant, which can lead to leaking API keys, OAuth tokens, conversation history, and credentials. [...]

Researchers detailed a souped-up version of the GoBruteforcer botnet that preys on servers with weak credentials and AI-generated configurations.

Cybersecurity researchers have documented four new phishing kits named BlackForce, GhostFrame, InboxPrime AI, and Spiderman that are capable of facilitating credential theft at scale