Attackers can inject indirect prompts in normal-looking repositories to trick Claude Code into spawning a reverse shell.
Mozilla’s 0din team showed how a Claude Code malware GitHub repo attack could use a clean-looking repository to open a ...
A new report reveals that AI agents can autonomously execute ransomware attacks, evidenced by the case of JADEPUFFER, which ...
According to researchers at cybersecurity companies Sekoia and YesWeHack, the packages are hosted on the Python Package Index (PyPI), a platform used by Python developers to source and share code.
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.
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 ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results