Hacker News Reader

macOSCryptoAIon Comet AI browser can get prompt injected from any site, drain your bank account

Check out the current Month of AI Bugs site... many such cases:

macOSCryptoAIon GitHub MCP exploited: Accessing private repositories via MCP

Was wondering about that, that part seems missing... Isn't there at least one time the user must approve the interaction with the MCP server and data sent to it?

The existence of a "Allow always" is certainly problematic, but it's a good reminder that prompt injection and confused deputy issues are still a major issue with LLM apps, so don't blindly allow all interactions.

macOSCryptoAIon Data Exfiltration from Slack AI via indirect prompt injection

Yes, images! And also link unfurling in bots. This researcher here talked about it before and also found tons of such data exfil issues in various LLM apps: https://embracethered.com/blog/posts/2024/the-dangers-of-unf...

macOSCryptoAIon OpenAI board in discussions with Sam Altman to return as CEO

An Uber self-driving car killed a person.