Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Fun fact: Copilot gives you no way to ignore sensitive files with API keys, passwords, DB credentials, etc.: https://github.com/orgs/community/discussions/11254#discussi...

So by default you send all this to Microsoft by opening your IDE.



Separate fun fact: Gemini CLI blocks env vars with strings like 'AUTH' in the name. They have two separate configuration options that both let you allow specific env vars. Neither work (bad vibe coding). Tried opening an issue and a PR, and two separate vibe-coding bots picked up my issue and wrote PRs, but nobody has looked at them. Bug's still there, so can't do git code signing via ssh agent socket. Only choice is to do the less-secure, not-signed git commits.

On top of that, Gemini 3 refuses to refactor open source code, even if you fork it, if Gemini thinks your changes would violate the spirit of the intent of the original developers in a safety/security context. Even if you think you're actually making it more secure, but Gemini doesn't, it won't write your code.


Gemini also won't help you with C++ if you are under 18, since it would be unsafe.

https://news.ycombinator.com/item?id=39632959


Is it still true? That's two years old


It's improved significantly in that time, but relative to the other frontier models, it is still the one that is the most condescending and coddling.


I use Gemini 3 to edit multiple forks. Your statement is false based on stuff I actually do.


Well it's true based on my running into the issue 8 hours ago


Maybe it's your prompts? I've never had Gemini refuse to write any code in any context. I use it with Claude prompts, edited down, in particular to remove guardrails.

You shouldn't use Google Ai products, they are inferior. Their models are quite good. It's confusing when people use the model name when referring to a product. What's your setup?


Fun fact: you shouldn't have sensitive files with API keys, passwords, DB credentials, etc. in your repo


“In your repo” and “in the directory you are running copilot” are two separate things.


It’s fine to have them in your repo if they’re encrypted and the private key isn’t in there as well!


Sadly, this issue is systemic: https://github.com/openai/codex/issues/2847


OpenCode has a plugin that lets you add an .ignore file (though I think .agentignore would be better). The problem is that, even though the plugin makes it so the agent can't directly read the file, there's no guarantee the agent will try to be helpful and do something like "well I can't read .envrc using my read tool, so let me cat .envrc and read it that way".


This points out that agentic security flaws are worse than "systemic", they're the feature. Agents are literal backdoors.

It's so bizarre to be discussing minor security concerns of backdoors, like trying to block env vars. Of course the maintainers don't care about blocking env vars. It's security theater.


I swear I just set up enterprise and org level ignore paths.


Yeah, it's a Copilot Business/Enterprise feature




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: