AgentShield
PulseAugur coverage of AgentShield — every cluster mentioning AgentShield across labs, papers, and developer communities, ranked by signal.
-
Security flaw in Gemini exposed users for three months
A security researcher highlighted a significant three-month vulnerability window for Google's Gemini, during which an exploit could have been used to hijack the voice assistant and execute malicious actions on a user's …
-
AI agents vulnerable to 'tool poisoning' via malicious descriptions
A recent article in VentureBeat highlighted a critical security vulnerability in AI agents, termed "tool poisoning," where malicious instructions are embedded within a tool's description rather than user input. This all…
-
AgentShield launches spending firewall to control AI agent financial expenditures
AgentShield has launched a new spending firewall system aimed at managing the financial expenditures of AI agents. This tool is designed to monitor and control transactions initiated by autonomous AI systems, addressing…