Google fixed Rogue Agent, a Dialogflow CX Code Blocks flaw that could let one writable agent affect every chatbot in a Cloud ...

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

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

AI Now’s Friendly Fire PoC shows Claude Code and Codex running README-planted payloads on hosts when autonomous command ...

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

A threat group researchers call "Armored Likho" has gained access to government agencies and electrical power entities in ...

The FBI warned that TeamPCP software supply chain attacks targeted developer tools to steal cloud credentials, SSH keys, and ...

Researchers at Sysdig say an AI agent called JADEPUFFER carried out a fully autonomous ransomware attack in just 31 seconds, exploiting a Langflow CVE-2025-3248 flaw, adapting to failed exploits in ...

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 ...

Varonis reported the flaw to Google in late 2025 and it has been addressed, but it reminds defenders to take a look at their ...

Mozilla researchers revealed a new attack that tricks Claude Code into running hidden commands from seemingly harmless GitHub ...