This website uses cookies
Read our Privacy policy and Terms of use for more information.
Jun 17, 2026
•
6 min read
This week every structural blind spot in AI security shared one disconnected endpoint: the global stakes. The discourse won't connect macro AI risk to concrete failure - so the government did it by force. Plus: a prediction we called five weeks ago just landed.
Jun 15, 2026
4 min read
The Miasma/Hades worm hijacks four AI coding tools with one commit - no install required. LiteLLM hits CISA's KEV under active ransomware attack. And a NIST proof says no guardrail set can ever block every jailbreak.
Jun 10, 2026
5 min read
Last week's structural blind spot didn't close. It jumped platforms - Apple to Meta - in seven days. Plus: we score our first prediction, and we got it wrong.
Jun 8, 2026
A HuggingFace RCE that defeats trust_remote_code. Google's MCP connector hijacked via CORS. 770+ exploitable flaws across 19,000 MCP servers. The protocol everyone rushed to adopt is the soft underbelly.
Jun 3, 2026
9 clusters, one orphan - the surface users actually touch is walled off from everything securing it, and a KEV-listed gateway bug proves the point.
Jun 1, 2026
3 min read
Starlette auth bypass hits vLLM, LiteLLM, and MCP gateways. SymJack lands six AI coding agents. First LLM-agent-driven intrusion captured in production.
May 27, 2026
Network analysis of this week's AI security discourse reveals a structural blind spot - and the EPSS top-50 confirms it.
May 25, 2026
TeamPCP. OpenAI. TrustFall. ChromaDB. Five critical AI security stories in one week.
May 10, 2026
1 min read
Same plan, one week later. Here's why.
May 3, 2026
2 min read
Two focused briefings. Original analysis. Public forecast accuracy. Here's what's coming.
Mar 12, 2026
19 min read
This week’s Secure Prompt: OpenClaw flaws expose agent runtimes, prompt injection moves into real-world web content, and AI security shifts from model misuse to operational control.
Mar 4, 2026
20 min read
This week’s Secure Prompt: AI-enabled attacks surge 89%, GenAI tools exploited across 90+ organizations, and GitHub Copilot prompt injection enables remote code execution.
