Research
- June 18, 2025Our latest research provides a framework for understanding agentic AI systems, outlines their core characteristics, and examines the security implications surrounding their use.June 12, 2025Trend Vision One™ tackles 7 of OWASP’s Top 10 LLM vulnerabilities, offering comprehensive protection against prompt injection, data leakage, AI supply chain risks, and other critical flaws.June 05, 2025Our research examines how AI coding assistants can hallucinate plausible but non-existent package names—therefore enabling slopsquatting attacks—while also providing practical defense strategies that organizations can implement to secure their development pipelinesMay 28, 2025To conclude our series on agentic AI, this article examines emerging vulnerabilities that threaten AI agents, focusing on providing proactive security recommendations on areas such as code execution, data exfiltration, and database access.May 21, 2025How can attackers exploit weaknesses in database-enabled AI agents? This research explores how SQL generation vulnerabilities, stored prompt injection, and vector store poisoning can be weaponized by attackers for fraudulent activities.May 13, 2025In the third part of our series we demonstrate how risk intensifies in multi-modal AI agents, where hidden instructions embedded within innocuous-looking images or documents can trigger sensitive data exfiltration without any user interaction.May 05, 2025Our research examines vulnerabilities that affect Large Language Model (LLM) powered agents with code execution, document upload, and internet access capabilities. This is the second part of a series diving into the critical vulnerabilities in AI agents.April 22, 2025This introductory post kicks off a blog series on AI agent vulnerabilities, outlining key security risks like prompt injection and code execution, and sets the stage for future parts, which will dive deeper into issues such as code execution flaws, data exfiltration, and database access threats.