Attackers can inject indirect prompts in normal-looking repositories to trick Claude Code into spawning a reverse shell.

A new report reveals that AI agents can autonomously execute ransomware attacks, evidenced by the case of JADEPUFFER, which ...

Mozilla’s 0din team showed how a Claude Code malware GitHub repo attack could use a clean-looking repository to open a ...

Retrieval-augmented generation enhances the performance of AI agents by expanding their recall. It can do this in three ...

Sysdig says JADEPUFFER used CVE-2025-3248 in Langflow to automate intrusion, credential theft, encryption, and data wipe.

The offices of Google are pictured in London on February 28, 2026. JUSTIN TALLIS/AFP via Getty Images Google released agents-cli on April 21, 2026, and it has shipped 13 updates in the 71 days since — ...

Meta's new Pocket app lets users create and share interactive mini-games using plain text prompts, making vibe coding ...

Multiple weaponized proof-of-concept (PoC) exploits on GitHub delivered a Python-based remote access trojan (RAT) called ChocoPoC that can execute commands and steal sensitive data. However, ChocoPoC ...

Attackers exploited Langflow vulnerability CVE-2025-3248 to conduct an agentic AI-powered ransomware attack involving reconnaissance, credential theft, and lateral movement.

A campaign active since last November has been targeting Python developers building Telegram bots with trojanized Pyrogram ...

Armored Likho BusySnake Stealer, a Python-based infostealer first disclosed by Kaspersky, is actively targeting government ...

They're not bad; they're just prompted that way. Sysdig threat hunters documented what they say is the first-ever documented ...