Stack layer / Threat pattern
GitHub Ships CodeQL 2.26.0 With AI Prompt-Injection Detection for JavaScript/TypeScript
GitHub (CodeQL release notes)
Stack layer / Threat pattern
AWS open-sources Loom, an enterprise agent platform built on Strands Agents + Bedrock AgentCore Runtime
AWS Open Source Blog
Stack layer / Threat pattern
Unit 42: AI-agent npm packages become a prime supply-chain target in H1 2026
Unit 42 (Palo Alto Networks)
Policy dependency / Stack layer
Commerce Department Lifts the Export Controls That Took Fable 5 and Mythos 5 Offline
Last Week in AI (Skynet Today)
Stack layer / Update thread
Mozilla Ships Tabstack, a Browser-Execution API Built for AI Agents
Product Hunt
Stack layer / Threat pattern
Scan for MCP prompt injection at a centralized control plane, and treat every tool response as untrusted
Obot AI
Policy dependency / Stack layer
Vercel Ships the Agent-Ops Layer: 'Eve' Framework for Natural-Language Agent Skills and 'Vercel Sandbox' to Fence In Data Access
The AI Insider
Stack layer / Update thread
Grok 4.5 Is the First Frontier Model Co-Trained With Cursor
xAI