Red Packet Security
PulseAugur coverage of Red Packet Security — every cluster mentioning Red Packet Security across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
China-linked threat actors weaponize new vulnerabilities within 24 hours
Threat actors with suspected ties to China have been observed exploiting newly discovered vulnerabilities within a day of their release. These actors are reportedly leveraging these exploits to gain unauthorized access …
-
Chinese actor weaponizes DeepSeek AI for automated cyberattacks · 4 sources tracked
A Chinese threat actor has reportedly weaponized an AI model developed by DeepSeek to automate cyberattacks. Researchers intercepted the AI agent as it attempted to compromise over 1,200 hosts for proxyjacking, a techni…
-
Global AI Red Teaming Initiative Launched for Enhanced Security
Red Packet Security is advocating for a global, collaborative approach to AI red teaming to bolster AI security. The initiative, termed "Red-Teaming in the Public Interest," aims to foster cooperation among researchers …
-
AI Agents Face New Security Challenges as They Gain Action Capabilities
Red Packet Security has published two articles discussing the security implications of AI agents. The first article focuses on the transition of AI tools from passive information consumption to active execution, highlig…
-
Securing AI Memory: Risks and Governance in Advanced AI
The concept of "AI memory" is crucial for understanding and securing advanced artificial intelligence systems. This memory allows AI models to retain information and context, which is essential for complex tasks and con…
-
AutoJack vulnerability allows RCE on AI agent hosts
A security vulnerability dubbed AutoJack has been discovered, allowing a single web page to gain remote code execution (RCE) on the host running an AI agent. This exploit targets frameworks like AutoGen, which are used …
-
Researchers Develop Playbook for Reconstructing AI Activity in Investigations
Security researchers are developing methods to reconstruct and analyze AI activity within investigations. This involves tracking AI telemetry and activity logs, particularly within platforms like Microsoft 365 Copilot a…
-
AI agent frameworks face RCE vulnerabilities from prompt injection attacks
Security researchers have identified critical remote code execution (RCE) vulnerabilities within several popular AI agent frameworks. These flaws stem from improper handling of user-supplied prompts, which can be manipu…