obliviasimplex

Hey guys, I'm the one who wrote the post and the Ghidra plugin. Really delighted to see it get so much traction here! I just merged a couple of PRs which should improve the tool somewhat -- one from eShuttleworth, which uses GPT-3's feedback to automatically rename the function and global variables, and another from me, which does the same for what Ghidra internally refers to as HighVariables (variables visible in the decompiled code listing, as opposed to just the assembly listing). Turns out these two things only look like similar operations from the perspective of the GUI.

Here's the public github repo: <https://github.com/tenable/ghidra_tools> Please feel free to fork it and send me PRs with any features or fixes you think might be useful.

Hey, thank you! I see that AlbertoGP's already gone ahead and boosted the post over here https://news.ycombinator.com/item?id=34250872#34256899, but I'd still be happy to send you an email.

You can actually try adding "and indicate what security vulnerabilities are present in the code, if any" or something to that effect to the prompt, by tweaking the `EXTRA` global variable defined near the head of the script. My experience with this so far is that it tends to spew out infosec truisms that aren't closely connected with the code, and that most interesting vulnerabilities require a bit more contextual awareness to notice than this tool has available to it, but ymmv, and it's definitely worth taking a bit of time to see if you can massage the prompt to finagle useful bughunting output from the tool.

Thanks for boosting this!

Fair point. It was a quick and dirty workaround, in the absence of `requests` in Ghidra's Jython distribution, but it turns out that `httplib` is available, and the latest commit uses that to do the HTTP request instead.

This is a cool idea! Definitely going to try giving it a whirl.

A Ghidra plugin that solicits GPT-3 for high-level commentary on decompiled code.