June 4, 2026
100 enterprise AI agents rated, plus an open source methodology you can use in procurement and security posture tracking.
Read more: AIRQ: AI Risk Quadrant — independent AI agent security rating (opens in new tab)June 4, 2026
100 enterprise AI agents rated, plus an open source methodology you can use in procurement and security posture tracking.
Read more: AIRQ: AI Risk Quadrant — independent AI agent security rating (opens in new tab)June 4, 2026
100 enterprise AI agents rated, plus an open source methodology you can use in procurement and security posture tracking.
Read more: AIRQ: AI Risk Quadrant — independent AI agent security rating (opens in new tab)
16 posts in Agentic AI Security Digest · Browse all posts
September 4, 2026
37 agentic AI security resources from August 2026: 19 unauthorized agent actions in a government eval, OpenAI's rogue swarm, and memory poisoning filters miss.
July 31, 2026
Four teams broke production AI agents in ten days. Twenty resources on the Kiro RCE, Cursor's CVSS 9.8 pair, memory poisoning, and sandbox escapes.
July 2, 2026
July 2026's agentic AI security roundup: agentic zero trust whitepapers, AutoJack & other new exploits, and the newest agent defenses.
June 1, 2026
28 agentic AI security resources from June 2026: coding agent RCEs, Microsoft Semantic Kernel flaws, a Copilot backdoor, and the defenses proposed against them.
May 4, 2026
May 2026 in agentic AI security: 40 resources on in-the-wild exploits, the Claude Code source leak, and vendors quietly patching their autonomous agents.
April 1, 2026
April 2026 in agentic AI security: privilege escalation in OpenClaw, the hijacking of Chrome's Gemini Live assistant, and the RSA conversation around both.
March 3, 2026
March 2026 in agentic AI security: 27 resources on the OpenClaw rush, identity files like SOUL.md, memory poisoning, and GitHub Copilot vulnerabilities.
February 4, 2026
February 2026 in agentic AI security: agent hijacking as a primary attack vector, the BodySnatcher flaw in ServiceNow, and the persistent ZombieAgent exploits.
January 7, 2026
January 2026 in agentic AI security: fresh research, defense methodologies and training, as exploits move from text manipulation to systemic tool poisoning.
December 12, 2025
19 agentic AI security resources from December 2025: AWS's Agentic AI Security Scoping Matrix, BrowseSafe on browser-agent injection, and Fact2Fiction.
November 10, 2025
22 agentic AI security resources from November 2025: the Cursor case-sensitivity RCE (CVE-2025-59944), OpenAI Atlas omnibox injection, and CompressionAttack.
October 6, 2025
Explore the Top Agentic AI Resources to stay informed about the most pressing risks and defenses in the field.
