Related Threat Clusters
-
AI Supply Chain Attacks and Model Poisoning Threats
In July 2026, researchers demonstrated that open-weight AI models can be easily poisoned, allowing attackers to implant backdoors for under $100. Katie Paxton-Fear successfully manipulated a model to execute remote code…
8 articles · Updated July 17, 2026 -
Microsoft and Salesforce Address AI Agent Data Exfiltration Vulnerabilities
Microsoft and Salesforce have patched serious prompt injection vulnerabilities in their AI platforms, Copilot Studio and Agentforce, respectively. Capsule Security identified these flaws, allowing attackers to…
6 articles · Updated April 15, 2026 -
AI Agents Vulnerable to Zero-Click Attacks: A Growing Threat
Michael Bargury, CTO of Zenity, revealed that enterprise AI agents are highly susceptible to zero-click attacks, which exploit their gullibility. These attacks can manipulate AI systems like Cursor, Salesforce, and…
2 articles · Updated March 23, 2026 -
CrowdStrike Enhances AI Security for Endpoints Amid Rising Threats
CrowdStrike announced new AI security features at RSA 2026, focusing on endpoint protection as AI applications proliferate. The Falcon platform now includes EDR AI Runtime Protection, which monitors commands and…
116 articles · Updated March 25, 2026
Recent Intelligence Reports
- Lethal Trifecta — simonwillison.net · July 17, 2026
- Copilot flaw — www.capsulesecurity.io · April 15, 2026
- Pipeleak The Lead That Stole Your Database Exploiting Salesforce Agentforce With Indirect Prompt Injection — www.capsulesecurity.io · April 15, 2026
- Copilot and Agentforce fall to form — Csoonline · April 15, 2026
- Microsoft, Salesforce Patch AI Agent Data Leak Flaws — Darkreading · April 15, 2026
- AI agents are 'gullible' and easy to turn into your minions — Theregister · March 23, 2026
- CrowdStrike Brings AI Security to the Endpoint — Msspalert · March 23, 2026