## When AI Agents Become the Supply Chain: Hidden Control Planes in Agentic Systems

**Categories:** Agentic AI, AI Risks  
**Date:** Aug 20th, 2026  
Three attack cases show how AGENTS.md files, marketplace skills, and dependencies give AI agents unauthorized authority, and what to test before trusting one.

## The Agentic AI Attack Surface: Where Risk Lives Beyond the Prompt

**Categories:** Agentic AI, AI Risks  
**Date:** May 5th, 2026  
Technical analysis of agentic AI security boundaries covering content ingestion, context translation, tool execution, and behavioral constraints in AI runtimes.

## From Trivy to LiteLLM: Expanding the LLM Supply Chain Threat Model

**Categories:** Industry News, AI Risks  
**Date:** Mar 25th, 2026  
The Trivy breach and LiteLLM compromise show how LLM supply chain risk now extends from malicious packages to CI, middleware, prompts, and data.