This website uses cookies
Read our Privacy policy and Terms of use for more information.
All of our previous posts
Jul 19, 2026
•
6 min read
How a Jailbroken Gemini Rewrote the Perimeter
Cyber Security
+2
Jul 12, 2026
AI phishing, hallucinated dependencies and prompt injection in developer toolchains
Jul 5, 2026
7 min read
Agentic ransomware, coding agent supply chain risk, and prompt injection against AI browsers
SEC://
Jun 28, 2026
12 min read
Amazon Q flaws, poisoned OpenAI tenants and Gaslight malware show AI threats moving into developer trust boundaries.
Jun 21, 2026
Poisoned agent skills, AutoJack and LiteLLM flaws reveal how AI control planes turn misplaced trust into enterprise compromise.
Jun 14, 2026
8 min read
New attack class achieves 85% compromise rate against autonomous AI agents in development pipelines. Prompt injection emerges as reliable exploitation vector.
Jun 7, 2026
9 min read
From Meta's hijacked support bot to a free LLM worm spreading through enterprise networks - how AI's trust models became this week's attack surface.
May 31, 2026
An LLM agent autonomously emptied a database in under two minutes, while RCEs in AI orchestration runtimes and coding agents widened the attack surface.