Microsoft Purview Data Loss Prevention
Purview DLP helps prevent data exfiltration by monitoring and controlling data transfers, relevant for AI agent attacks.
Purview DLP helps prevent data exfiltration by monitoring and controlling data transfers, relevant for AI agent attacks.
Entra Agent ID provides identity management for AI agents, helping to enforce least privilege and monitor actions.
Defender for Cloud offers security monitoring and threat protection for cloud environments, including AI agent activities.
Adversa AI demonstrated a full end-to-end attack against the production Plandex binary, exploiting the GuardFall bypass to execute malicious shell commands.
Hermes, an AI-powered framework, was used alongside OpenClaw to deploy sub-agents for various intrusion tasks, including SSO exploitation and API scanning, in…
OpenClaw has a vulnerability that allows any website to take full control of a developer's AI agent via WebSocket connections to localhost.
OpenClaw, formerly Clawdbot and Moltbot, is an open-source autonomous assistant used in mind virus experiments. Its default soul file was exploited in…
Two security teams have demonstrated that OpenClaw, a popular self-hosted AI agent, can be tricked into executing attacker-controlled code or leaking sensitive…
Cybersecurity researchers at Check Point have disclosed three now-patched security flaws in LangGraph, an open-source framework by LangChain for building stateful, multi-agent…
Microsoft researchers have disclosed a novel exploit chain named AutoJack that allows a single malicious web page to hijack an AI browsing…