This website uses cookies
Read our Privacy policy and Terms of use for more information.
Feb 26, 2026
•
18 min read
This week’s Secure Prompt: mass Claude model distillation exposed, prompt injection moves operational via supply-chain compromise, and AI-generated passwords proven predictably weak.
Feb 20, 2026
19 min read
This week’s Secure Prompt: OpenClaw Control UI hijacking enables agent takeover, 0-click RCE hits AI desktop connectors, and a CVSS 9.8 RAG supply-chain flaw exposes autonomous workflows.
Feb 13, 2026
This week’s Secure Prompt: vLLM RCE exposes millions of AI servers, OpenAI declares prompt injection "unfixable," and AWS breached via LLM in 8 minutes.
Feb 4, 2026
This week’s Secure Prompt: Hijacked LLMs, fake Moltbot extensions, MCP auth gaps, and why agent security is breaking faster than defenses.
Jan 30, 2026
13 min read
I Built My Own AI Agent This Week. Here's What I Learned (The Hard Way).
Jan 9, 2026
2 min read
The AI security incidents, vulnerabilities, research, and regulations that defined 2025 - curated in one place.
Dec 24, 2025
4 min read
A year-defining week for AI security, a thank-you to our first subscribers, and a short holiday pause before we return in January.
Nov 30, 2025
This week’s Secure Prompt: DeepSeek political triggers, AI attack automation, sandbox escapes, poisoning-at-scale, deepfakes-as-a-service, and more.
Nov 19, 2025
6 min read
This week’s Secure Prompt: AI-Orchestrated Cyber Espionage: Inside GTG-1002.
Nov 12, 2025
21 min read
This week’s Secure Prompt: HackedGPT, Whisper Leak, Claude flaws, AI ransomware, deepfake espionage, and more.
Nov 5, 2025
23 min read
This week’s Secure Prompt: Copilot Mermaid injection, agent data leaks, MCP hijacking, AI receipt fraud, Claude exfil - and more.
Oct 29, 2025
22 min read
This week’s Secure Prompt: Copilot injection flaw, ChatGPT Tainted Memories, AI ransomware, CompressionAttack, and more.
