Lilli System Github We argue that this incident constitutes a watershed moment in ai security: the first publicly documented case of an autonomous ai agent compromising another organization's production ai system end to end, without any form of human assistance. Mckinsey & company — the world's most prestigious consulting firm — built an internal ai platform called lilli for its 43,000 employees. lilli is a purpose built system: chat, document analysis, rag over decades of proprietary research, ai powered search across 100,000 internal documents.
Free Lilli Github Tl;dr — mckinsey’s ai platform lilli was breached in two hours by a $20 autonomous agent. 46.5 million internal messages and 728,000 client files exposed. the agent didn’t break any perimeter — it found an unauthenticated api, chained a sql injection, and read directly from the production database. Mckinsey, a sprawling global management consultancy, built an internal ai platform called lilli back in 2023. it’s a purpose built system: chat, document analysis, rag (retrieval augmented generation) over decades of proprietary research, and ai powered search across 100,000 internal documents. Testers of only a primitive lilli prototype immediately leveraged it for everything from data analysis to planning and creative problem solving. this indicated that lilli could become a platform on which we build gen ai–based applications that completely rewire the way we operate. Understand how an ai agent hacked mckinsey’s internal ai platform ‘lilli’, and the lessons organizations should take from this exercise.
Lilli 2048 Github Testers of only a primitive lilli prototype immediately leveraged it for everything from data analysis to planning and creative problem solving. this indicated that lilli could become a platform on which we build gen ai–based applications that completely rewire the way we operate. Understand how an ai agent hacked mckinsey’s internal ai platform ‘lilli’, and the lessons organizations should take from this exercise. Description: codewall reported that its autonomous agent exploited vulnerabilities in mckinsey's lilli ai platform and obtained unauthorized read and write access to production systems, allegedly exposing internal chat messages, files, user accounts, and prompts. Lilli, named after lillian dombrowski mckinsey's first female consultant, aggregates information from over 40 knowledge sources and 100,000 documents, acting as a centralized knowledge hub. it aims to reduce research time, improve knowledge sharing, and enhance client value. Github is where lilli system builds software. people this organization has no public members. you must be a member to see who’s a part of this organization. Lilli isn’t just a tool—it’s part of the operating system mckinsey uses to deliver faster, smarter, and better results for its clients. what makes lilli stand out is its ability to become part of daily work.
Github Lilli5 Project Description: codewall reported that its autonomous agent exploited vulnerabilities in mckinsey's lilli ai platform and obtained unauthorized read and write access to production systems, allegedly exposing internal chat messages, files, user accounts, and prompts. Lilli, named after lillian dombrowski mckinsey's first female consultant, aggregates information from over 40 knowledge sources and 100,000 documents, acting as a centralized knowledge hub. it aims to reduce research time, improve knowledge sharing, and enhance client value. Github is where lilli system builds software. people this organization has no public members. you must be a member to see who’s a part of this organization. Lilli isn’t just a tool—it’s part of the operating system mckinsey uses to deliver faster, smarter, and better results for its clients. what makes lilli stand out is its ability to become part of daily work.
Comments are closed.