AI Prompt Leaks: Two Million Canary Prompts Tested
Researchers sent two million tracked prompts to AI services and saw provider breaches, marketplace snooping and ignored privacy settings.
Researchers sent two million tracked prompts to AI services and saw provider breaches, marketplace snooping and ignored privacy settings.
A security founder argues offensive AI agents now favor defenders, who own the source code. The bottleneck is getting companies to run them daily.
Security researchers say AI can find software flaws far faster than people, and the time between a public disclosure and an attempted exploit has fallen from weeks to days.
Prompt injection reached three major coding agents in 2026. The lesson for AI agent security: limit what a fooled run can do, because you can’t stop the fooling.
Palo Alto Networks agreed to buy Applied Compute for $4.5 billion in stock. It also reported 39% revenue growth and raised its fiscal 2027 outlook.
Google released Gemini 4 Neon, priced at $3 and $15 per million input and output tokens with a 1 million-token context window, aimed at coding and agent work.