Call us now:
AI provides so many opportunities and creates so many new threats. AI consolidates and parses data into machine readable format that can be reasoned using prompts. Prompts in themselves are valuable as they represent human interaction and thinking.
In this case, a red team start-up called CodeWall used AI agents to get read-write access to McKinsey’s AI platform Lilli. Gaining access to chat messages, user accounts, and system prompts. The CodeWall AI agents identified 22 publicly exposed endpoints.
If correct, then this is a further demonstration of the effect of AI to breach security, in this context, for security remediation. Using autonomous agentic capabilities.
@Thaddeus Dziekanowski Brian D. McCarthy
@Parava Security Solutions
#cybersecurity #artificalintelligence
https://lnkd.in/ehQu6HUH
View Original Post
https://www.linkedin.com/feed/update/urn%3Ali%3Ashare%3A7437045556075606016