​OpenAI has revealed that two artificial intelligence (AI) agents powered by GPT-6.1 Sol and one GPT-6 Astra weakened misalignment monitoring while making requested software changes during two internal coding tasks.… Read More »OpenAI’s GPT-6 Agent Removed Safety Monitoring, Then Falsely Denied Doing So

​The popular LiteLLM Python package has been compromised as part of a software supply chain attack that delivered a credential stealer and a backdoor, according to reports from SafeDep, Socket,… Read More »LiteLLM Compromised in Supply Chain Attack Delivering Credential Stealer and Backdoor

​PHP has released emergency updates that fix two critical flaws in the language itself, letting an attacker without an account run code on a web server. The fixes are in… Read More »PHP Issues Emergency Patches for Two Critical PHP2Shell RCE Flaws as Exploit Attempts Emerge

​Google on Tuesday said it’s rolling out improved safeguards in its Chrome browser to secure users against ClickFix attacks when Enhanced Protection is enabled. ClickFix is a popular social engineering… Read More »Google Chrome Adds ClickFix Warnings to Stop Users From Running Malicious Commands

​Generative AI has changed what a malicious email looks like. Messages that once gave themselves away through clumsy wording, generic pretexts, and reused templates now arrive fluent, personalized, and unique… Read More »Generative AI Is Erasing Behavioral Tells, Weakening Behavior-Only Detection, Proofpoint Reports

​Cybersecurity researchers have disclosed details of a previously undocumented China-aligned threat cluster known as Bronze Sandcastle that has been observed targeting organizations in Asia and Africa since mid-2025. “The most… Read More »China-Aligned Bronze Sandcastle Abuses Sandboxie DLL Sideloading to Deploy Backdoors

​Attackers took control of more than 300 Tor exit relays in early October and used them to redirect SSH connections to servers that stole login passwords, a researcher found. Exit… Read More »Attackers Hijacked Over 300 Tor Exit Relays to Intercept SSH Connections

​An AppSec team can point an AI agent running on a general-purpose model at its own web apps with little setup. Sure, the model writes the attacks. But everything that… Read More »The Harness Is the Hard Part of Agentic Pentesting

​You cannot fully block the two critical PHP flaws called PHP2Shell before today’s fix, and the one setting being passed around as a workaround is not enough on its own,… Read More »PHP2Shell: What Actually Protects You Before the 14:00 UTC PHP RCE Patch, and What Doesn’t