Intelligence brief

AI Security NOW

Daily news and practitioner analysis on AI, MCP, LLM, and agent security. Updated daily.

Last updated 8/25/2026

Engineering Analysis

Slopsquatting at Agent Speed: What Hallucinated Resolution Actually Breaks

This isn't a content-filtering problem you can scan your way out of — it's a naming-and-resolution problem baked into how agents decide what "real" means. Security teams need to stop treating hallucinated packages and skills as a model-quality bug and start treating agent resolution as an unauthenticated trust boundary.

BleepingComputer, Unit 42, Aikido Security/Aug 16, 2026/14 minutes

AI Security News

Latest vulnerabilities, agent threats, and research disclosures.

Full archive

Insights

Commentary from the AI security literature.

Research

Papers on MCP, agents, and LLM security.