macOSCryptoAI
Re:Comet AI browser can get prompt injected from any site, drain your ...
on Sunday August 24, 2025 @04:10PM (#45007343)
Check out the current Month of AI Bugs site... many such cases:
Re:Claude 4 and GitHub MCP will leak your private GitHub repositories
on Monday May 26, 2025 @09:09PM (#44103068)
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.
Sneaky Bits: Advanced Data Smuggling Techniques
Security ProbLLMs in XAI's Grok: A Deep Dive
Grok can leak your data
ZombAIs: From Prompt Injection to C2 with Claude Computer Use
Re:Attackers can exfil data with Slack AI
on Tuesday August 20, 2024 @08:52PM (#41305678)
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...
Re:OpenAI board in discussions with Sam Altman to return as CEO
on Saturday November 18, 2023 @09:16PM (#38327751)
An Uber self-driving car killed a person.