Microsoft researchers have detailed an exploit chain, named AutoJack, that turns an AI browsing agent into a delivery vehicle for remote code execution. Steer the agent […]
For years, security teams built their programs around a simple premise of if you control the identities, you can control the risk. Employees authenticate through […]
Two security teams have shown, in separate research published this week, that OpenClaw, the popular self-hosted AI agent, can be driven to run attacker-controlled code […]
It’s been one of those weeks. You expect the usual noise: recycled malware, sloppy attacks, another easy target getting hit. Instead, there’s a supply chain […]
Phishing simulation on an OpenClaw email agent with various configuration profiles showed that it was susceptible to tactics commonly used to compromise human users. The OpenClaw […]
Two things landed within days of each other this week. A security startup reported 21 previously unknown vulnerabilities in FFmpeg, the media library inside almost […]
An unknown threat actor has been observed using a large language model (LLM) agent to conduct post-compromise actions after obtaining initial access following the exploitation […]
On May 19th, 2026, Orchid Security released the results of our Identity Gap: Snapshot 2026. Among the findings, “identity dark matter” (the unseen, unmanaged elements […]
On February 17, 2026, the popular AI coding assistant Cline CLI (formerly Claude Dev) was the target of a supply chain attack where an unauthorized version, [email protected], was […]
© Bulletproof Servers. All rights reserved.