Embrace The Red
21 briefings written from Embrace The Red's reporting, newest first. Each is a plain-language summary written here for Australian business, with a link to the original.
- Patched Flaw Let Copilot in Visual Studio and SSMS Run Commands on Developer Machines
- Patched Flaw in Visual Studio and SSMS Copilot Let a Trailing Dot Defeat Its Safety Checks
- Critical SQL Server Flaw Shows How AI Assistants Can Inherit Powerful Database Privileges
- Critical Flaw in Microsoft's SQL Copilot Could Let Attackers Escalate to Admin
- Researcher Says Claude Code's Auto Mode Can Be Hijacked by a Simple Website Summary Request
- Researcher Finds Claude Code's 'Auto Mode' Can Be Tricked Into Running Malicious Code
- Researchers Show Encrypted AI 'Reasoning Traces' Can Be Exposed, Leaking Passwords and Personal Data
- Encrypted AI Reasoning Data Can Be Recovered, and It May Be Leaking Passwords
- Encrypted AI Reasoning Data Can Be Recovered, and Shared Session Files May Leak Secrets
- AI Gateways Like LiteLLM Are a High-Value Target: Red Team Research Shows How Traffic Could Be Rerouted and Altered
- AI Gateways Like LiteLLM Are Becoming Prime Targets for Attackers
- AI Gateways Are a High-Value Target: How Attackers Could Reroute and Tamper with Your AI Traffic
- PipeWire Flaw Lets Attackers Escape Linux Sandboxes via Audio Access
- Linux Audio Flaw Lets Sandboxed Apps Break Out and Reach Your Desktop, Files and Credentials
- AI Agent Drove Hugging Face Breach, and Defenders Hit an Unexpected Roadblock
- AI Agent Behind Hugging Face Breach Signals a New Kind of Intruder
- Apple Patches macOS Terminal Flaw Used to Sneak Data Out via DNS Requests
- Apple Fixes macOS Terminal Flaw That Let AI Tools Be Tricked Into Leaking Data via DNS
- Apple Fixes macOS Terminal Behaviour That Let AI Tools Leak Data Through DNS
- AI Agents Can Be Tricked Into Clicking the Wrong Button, Researcher Shows
- AI Agents Are Getting Alarmingly Good at Finding and Exploiting Software Bugs