AI vs AI: Agent hacked McKinsey's chatbot and gained full read-write access in just two hours
ID: 9990864c-c85a-5eb2-a705-cd5ddf975d64
STIX ID: report--9990864c-c85a-5eb2-a705-cd5ddf975d64
Feed Name: The Register (Security)
Threat Score
CodeWall's autonomous AI agent discovered unauthenticated API endpoints and exploited an SQL injection in McKinsey's Lilli chatbot, reportedly gaining read/write access to production data (46.5M chat messages, 728K files, 57K accounts) and writable system prompts that could enable prompt poisoning; McKinsey patched the vulnerabilities quickly and says forensic review found no evidence of client-data access.
Your team is not currently subscribed to this feed. You must subscribe to it in order to see this post.