[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

![karpathy Avatar](https://lunarcrush.com/gi/w:24/cr:twitter::33836629.png) Andrej Karpathy [@karpathy](/creator/twitter/karpathy) on x 1.3M followers
Created: 2025-06-16 17:02:51 UTC

I should clarify that the risk is highest if you're running local LLM agents (e.g. Cursor, Claude Code, etc.).

If you're just talking to an LLM on a website (e.g. ChatGPT), the risk is much lower *unless* you start turning on Connectors. For example I just saw ChatGPT is adding MCP support. This will combine especially poorly with all the recently added memory features - e.g. imagine ChatGPT telling everything it knows about you to some attacker on the internet just because you checked the wrong box in the Connectors settings.


XXXXXXX engagements

![Engagements Line Chart](https://lunarcrush.com/gi/w:600/p:tweet::1934657940155441477/c:line.svg)

**Related Topics**
[all the](/topic/all-the)
[mcp](/topic/mcp)
[open ai](/topic/open-ai)
[llm](/topic/llm)

[Post Link](https://x.com/karpathy/status/1934657940155441477)