ÚLTIMA HORA
10:00 Week in review: Java4Shell proves tricky to exploit, malware planted via Optimizely hits 178 orgs // Help Net Security06:06 OpenRouter Drops 3 Providers After Researchers Catch Months of Prompt Theft at AI Hosting Firms // The Hacker News06:03 Researchers Demonstrate Ghostscript Sandbox-Escape RCE via Crafted File Uploads in Popular Apps // The Hacker News01:53 FBI Investigating Apparent Hack of Its Key National Criminal Justice Database, AP Source Says // SecurityWeek23:59 Rackspace Spot breach let hackers access customer Kubernetes secrets // BleepingComputer19:22 Cyberattack on Austrian Foreign Ministry Exposes Diplomatic Staff Data // SecurityAffairs19:01 Microsoft Entra Connect Health flaw exploited to steal tenant data // BleepingComputer18:52 Vulnerabilities in nginx Affecting Cisco Products: November 2026 // Cisco PSIRT17:50 Cairn AI Framework Used in Autonomous Zero-Day Exploitation // SecurityAffairs17:09 U.S. CISA adds Cisco Expressway, SAP NetWeaver, Broadcom VMware vCenter, and Apache Roller flaws to its Known Exploited Vulnerabilities catalog // SecurityAffairs16:17 BADBOX 3.0 botnet returns with record-breaking 40 billion daily ad requests // BleepingComputer15:26 FBI reportedly hacked again, this time targeting nationwide police database // BleepingComputer

Modernising threat hunting: Using Semantic Search to Find Risky AI Agent Behavior

04/11/2026 · 13:45

I tested vector search on 7,454 turns of my own agent sessions. One in seven sessions needed review, the agent’s reasoning carried more signal than the prompt, and the stored vectors answer questions nobody thought to ask at ingest.

Source Elastic Security Labs · 4 November 2026, 13:45
Read the full story at Elastic Security Labs →

Summary generated automatically from the source feed. Full content and rights belong to its author.