News items I have found interesting and informative.
In the past 24 hours: a Copilot Chat flaw enabled prompt-injection-driven secret leakage, Discord reported a breach involving verification IDs, and DeepMind described an agent that finds and fixes vulnerabilities. Ukraine detailed surging AI-driven attacks, and BU’s LOKI ML system uncovered 52k scam sites; Taiwan warned of hybrid online warfare tactics.
In the past 24 hours: Redis patched a critical RCE flaw (RediShell), and OpenAI banned accounts tied to Chinese surveillance requests and misuse of DeepSeek. Google released its Secure AI Framework 2.0 and CodeMender agent, while the EU revealed new AI industry and science strategies.
In the past 24 hours, Redis patched a 13-year-old critical flaw affecting tens of thousands of servers, Atos launched an AI-powered SOC analyst, and global CISOs confirmed AI as their top investment priority. Oracle’s EBS zero-day exploitation continues to escalate.
Over the past 72 hours, a zero-day in Oracle EBS exploited by Cl0p prompted an emergency patch; the newly disclosed “CometJacking” exploit hijacks AI browser agents; and CISOs are redesigning security teams for AI risk. Extended context includes California’s new AI disclosure law and warnings about detection outpacing patch capacity.
Today’s briefing explores the fallout from CISA’s lapse in threat-sharing protections, the rise of AI-augmented “Bionic Hackers,” and increasing MCP standardization across enterprises. Extended coverage touches on DeepSeek model risks and the surge in generative AI insurance demand.
Today’s briefing covers the impact of CISA staff furloughs on U.S. cyber coordination, new AI-based ransomware detection in Google Drive, and Microsoft’s launch of a security marketplace. Extended context includes “vibe hacking” manipulations and Databricks’ new AI-driven threat analytics.
Today’s briefing spotlights serious vulnerabilities in Google’s Gemini assistant, Microsoft’s new unified AI security stack, and a CAISI evaluation of DeepSeek’s security weaknesses. Broader context from WEF emphasizes how AI is increasingly integral to both offense and defense in cybersecurity.
Today’s briefing covers California’s new AI safety law, fears over the lapse of CISA protections, and a passenger data leak at WestJet. Extended context includes risks from unmanaged AI agents, the patching backlog challenge, and Ant’s new AI SHIELD for finance.
Today’s briefing warns of critical Cisco ASA zero-days hit by a CISA emergency directive, SOC teams drowning in alerts, and a claimed Comcast breach by Medusa ransomware. AI-powered attack techniques and predictive protection in education signal shifts in both offensive and defensive strategy.
Today’s briefing highlights a critical Salesforce AgentForce vulnerability (ForcedLeak), and Google’s new Agent Payments Protocol (AP2) that allows AI agents to transact autonomously. Extended coverage includes U.S. policy debates around AI-China tension and Kuwait’s deployment of AI surveillance vehicles.
TECHMANIACS.com 