The AI security incidents, vulnerabilities, research, and regulations that defined 2025 - curated in one place.
A year-defining week for AI security, a thank-you to our first subscribers, and a short holiday pause before we return in January.
This week’s Secure Prompt: DeepSeek political triggers, AI attack automation, sandbox escapes, poisoning-at-scale, deepfakes-as-a-service, and more.
This week’s Secure Prompt: AI-Orchestrated Cyber Espionage: Inside GTG-1002.
This week’s Secure Prompt: HackedGPT, Whisper Leak, Claude flaws, AI ransomware, deepfake espionage, and more.
This week’s Secure Prompt: Copilot Mermaid injection, agent data leaks, MCP hijacking, AI receipt fraud, Claude exfil - and more.
This week’s Secure Prompt: Copilot injection flaw, ChatGPT Tainted Memories, AI ransomware, CompressionAttack, and more.
This week’s Secure Prompt: Shadow Escape, Gemini ASCII flaw, AI malvertising, Guardrails bypass, Shadow AI, and more.
This week’s Secure Prompt: CamoLeak, prompt-injection backdoors, LLM compromise research, AI agent risks, and more.
This week’s Secure Prompt: Gemini flaws, CometJacking, RL-Hammer attacks, fake Sora apps, motion-sensor spying, and more.
This week’s Secure Prompt: new AI security tools, GenAI deepfakes, a universal jailbreak bypassing LLM guardrails, and more.
This week’s Secure Prompt: zero-click AI vulns, GenAI deepfakes, and what 65% of IT leaders admit about their defenses.
