Severity: ElevatedAction: Be aware
AI Agents Aimed SQL Injection at US and Canadian Government Sites
The attacks targeted the US Department of Education and Library and Archives Canada, and researchers linked some agents to OpenAI.
Agent Security
Most important this week
Severity: Informational
doxx.net Raises $38 Million to Prevent AI Agent-on-the-Internet Misadventures
doxx.net’s new ADN platform prevents agentic misadventure while the agent is operating under the user’s authority.
Severity: HighAction: Review
Automated AI agent used to breach cybersecurity nonprofit DIVD
The Dutch Institute for Vulnerability Disclosure (DIVD) suffered an AI-driven cyberattack that the organization described as "loud and very, very messy."
All Agent Security stories
doxx.net Raises $38 Million to Prevent AI Agent-on-the-Internet Misadventures
Severity: Informational
AI Agents Aimed SQL Injection at US and Canadian Government Sites
Severity: ElevatedAction: Be aware
Autonomous AI agents tried to hack US, Canadian government websites
Severity: Informational
Secure what’s next: Your guide to Microsoft Security at Microsoft Ignite 2026
Severity: Informational
Anthropic Flags AI Agent Liability Risks as OpenAI Faces Hacking Lawsuit
Severity: ElevatedAction: Be aware
Automated AI agent used to breach cybersecurity nonprofit DIVD
Severity: HighAction: Review
Reco Raises $55 Million for Agentic Security
Severity: Informational
Rig Security Emerges From Stealth With $12M to Tackle Agentic AI Identity Risks
Severity: Informational
Nvidia Launches AI Agent Safety Platform to Prevent Rogue Activities
Severity: Informational
Carbonato Botnet Puts an AI Agent on Hacked Docker Hosts
Severity: ElevatedAction: Be aware
AI Agents Are Privileged Users; Who Is Auditing Their Access?
Severity: Informational
JadePuffer agentic AI attacks target Azure, destroy cloud resources
Severity: HighAction: Be aware
JadePuffer AI Actor Compromises Azure Tenant in Destructive Cloud Attack
Severity: ElevatedAction: Be aware
AI Sandbox Escapes: Why Forensic Readiness Matters More Than Containment
Severity: Informational
Storm-3168: Agentic-driven cloud attacks using compromised service principals
Severity: HighAction: Be aware
On Anthropic’s AI Misuse Report
Severity: ElevatedAction: Be aware
'Salesbleed' Exploits Salesforce Agents to Enable Slack Phishing
Severity: ElevatedAction: Be aware
What’s new in Microsoft Security: September 2026
Severity: Informational
3 Cyber Threats That Defined the Summer of 2026
Severity: HighAction: Be aware