Live data from Hacker News

Show HN: A MitM proxy to see what your LLM tools are sending

github.com

61–70 of 128 posts

Re: Show HN: A MitM proxy to see what your LLM tools are sending

#61

Could you use an approach like this much like a traditional network proxy, to block or sanitise some requests? E.g. if a request contains confidential information (whatever you define that to be), then block it?

I do kinda the opposite where I run my AI in a sandbox. it sends dummy tokens to APIs. the proxy then injects the real creds. so, the AI never has access to creds.

https://clauderon.com/ -- not really ready for others to use it though

Re: Show HN: A MitM proxy to see what your LLM tools are sending

#63
It’s actually really easy to use mitmproxy as a…proxy. You set it up as a SOCKS proxy (or whatever) and point your network or browser to the proxy. I did this recently when a python tool was too aggressive on crawling the web and the server would reject me. Forced my session to limit 5 requests per second and it worked rather than finding the exact file to change in the library. Just do the same to your browser and then turn on the capture mode and you’ll see the requests

Re: Show HN: A MitM proxy to see what your LLM tools are sending

#64

It’s actually really easy to use mitmproxy as a…proxy. You set it up as a SOCKS proxy (or whatever) and point your network or browser to the proxy. I did this recently when a python tool was too aggressive on crawling the web and the server would reject me. Forced my session to limit 5 requests per second and it worked rather than finding the exact file to change in the library. Just do the same to your browser and t…

The idea is to simplify and store it... Thinking of changing it to http relay, what do you think?

Re: Show HN: A MitM proxy to see what your LLM tools are sending

#67

This tool looks like it unconditionally disables tls verification for upstream requests. It shells out to mitmproxy with "--set", "ssl_insecure=true" This took all of 5 minutes to find reading through main.py on my phone. https://github.com/jmuncor/sherlock/blob/fb76605fabbda351828... Edit: In case it’s not clear, you should not use this.

Just fixed it and implemented a simple http relay, eliminating the mitmproxy and the ssl_insecure=true. The new implementation uses TLS verification, doing last tests and merging it... After the merge can you check it out and tell me if I earned your star? :D

Re: Show HN: A MitM proxy to see what your LLM tools are sending

#70
post #68
post #66

Amusingly, I had the same question and asked Claude Code to vibe code me something similar. :)

Now you can add on top of it :D and we can all create something great :D

As is the case with most vibe coded software, it wasn't polished, didn't work very well, had lots of edge cases, and was pretty much bespoke to my one use case. :)

It answered the question "what the heck is this software sending to the LLM" but that was about all it was good for.

Post reply on HN