When AI Trusts the Wrong Data: New Research From Prompt Security | Prompt Security

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

Agentic AI
AI Risks
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.

ChatGPT Security Guide: Enterprise Risks, Incidents, and Practitioner Guidance

AI Risks
AI Resources
Jun 29th, 2026
What security teams actually need to know about ChatGPT: data handling, documented incidents, CISO guidance, and API risks.

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

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