vulnerability
Microsoft fixes AutoGen Studio flaw that enabled code execution
Medium
Summary
A vulnerability, dubbed AutoJack, was discovered in Microsoft’s AutoGen Studio, a framework for building multi-agent AI systems. The flaw allowed attackers to execute arbitrary commands on a host system by manipulating an AI agent through a malicious webpage. Microsoft swiftly addressed the issue before any public release, limiting the impact to developers building AutoGen Studio from the main GitHub branch during a specific timeframe.
Summary written automatically in our own words from the original article, which belongs to its publisher and remains the reference. It may contain errors. Sources & data