From Stateless Queries to Autonomous Actions: A Layered Security Framework for Agentic AI Systems

Agentic AI systems face security challenges that stateless large language models do not. They plan across extended horizons, maintain persistent memory, invoke external tools, and coordinate with peer agents. Existing security analyses organize threats by attack type prompt injection, jailbreakin...

EUVD-2024-50032

Malicious code in bioql PyPI...

CVE-2024-9579

A potential vulnerability was discovered in certain Poly video conferencing devices. The firmware flaw does not properly sanitize user input. The exploitation of this vulnerability is dependent on a layered attack and cannot be exploited by itself...

CVE-2024-9579

A potential vulnerability was discovered in certain Poly video conferencing devices. The firmware flaw does not properly sanitize user input. The exploitation of this vulnerability is dependent on a layered attack and cannot be exploited by itself...

CVE-2024-9579 Certain Poly Video Conference Devices – Potential Remote Code Execution

A potential vulnerability was discovered in certain Poly video conferencing devices. The firmware flaw does not properly sanitize user input. The exploitation of this vulnerability is dependent on a layered attack and cannot be exploited by itself...

PT-2024-9534 · Poly · Poly Video Conferencing Devices

Name of the Vulnerable Software and Affected Versions: Poly video conferencing devices affected versions not specified Description: A potential issue was discovered in certain Poly video conferencing devices, related to the firmware not properly sanitizing user input. This can be exploited by a...