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

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

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

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

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

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 ...

A PNG hiding a prompt injection could steal your repo's secrets, researchers demonstrate. The technique, dubbed 'Ghostcommit, ...

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

Security tooling is not written in a single language. Python powers most automation. C sits at the exploit layer. PowerShell ...