🎧 Subscribe to the podcast feed Security News Self-Replicating Prompt Injections Found in GPT Models (The Register) — OpenAI's alignment team disclosed GPT models susceptible to worm-style prompt injection attacks that can propagate across agents and contexts. Apple CVE-2026-86950 Weaponised in Sophisticated Targeted Attacks (Dark Reading)…
🎧 Subscribe to the podcast feed Security News Apple Emergency Patch — CVE-2026-86950 (iOS 26, macOS 26, macOS 15) (SANS ISC) — Apple issued emergency security updates for iOS 26, macOS 26, and macOS 15 to address CVE-2026-86950; emergency patches of this kind typically follow confirmed in-the-wild…
🎧 Subscribe to the podcast feed Security News Citrix NetScaler ADC & Gateway — 8 CVEs including Unauthenticated RCE (Citrix / NVD) — Citrix published eight vulnerabilities (CVE-2026-88771 through CVE-2026-88778) affecting NetScaler ADC and Gateway; two are Critical (CVSS 4.0: 9.5) including an unauthenticated arbitrary command execution flaw…
Security Stories AI Agent Misbehavior — A Week of Unintended Consequences OpenAI had a difficult week for agent safety. The company disclosed that its AI agents accidentally uploaded user-provided images to third-party image-hosting services during research tasks — a data handling failure where user content ended up on infrastructure…
🎧 Subscribe to the podcast feed | Direct MP3 Security News ShinyHunters uses WAF bypass trick in Oracle PeopleSoft attacks (BleepingComputer / Mandiant) — ShinyHunters is now using URL percent-encoding (%50EMHUB instead of PSEMHUB) to bypass WAF rules mitigating CVE-2026-35273, allowing resumed exploitation of unpatched PeopleSoft servers and deploying the SIDEEYE…
🎧 Subscribe to the podcast feed | Direct MP3 Security News Kiteworks urges 6-hour server shutdown over potential zero-day attacks (BleepingComputer / The Record) — Secure file-sharing platform Kiteworks told customers worldwide to shut down servers on Saturday after receiving credible threat intelligence from federal intelligence agencies warning of an imminent…
🎧 Subscribe to the podcast feed Security News Crook used three open-source AI agents to breach Fortune 500 hospitality company, major US airline and 25+ orgs (The Register) — A threat actor chained three publicly available agentic AI frameworks to compromise over 25 organisations with no custom tooling or nation-state…
🎧 Subscribe to the podcast feed Security News FBI rushes to investigate if ShinyHunters hack of thousands of employees is real (Ars Technica) — The FBI has launched an urgent investigation into ShinyHunters' claim of breaching Criminal Justice, HR, and Medlink systems via Oracle PeopleSoft, with the group alleging 2–3TB…