Comment by yellow_lead

1 day ago

Yes, so there may be more of these too. But GitHub even declined to fix this.

Honestly it's for the best. People keep thinking it's safe to use AI tools without VM, credential, and network sandboxing, the same way a person who's "only buzzed" thinks it's safe to drive a car. I wouldn't trust an agent's heuristics any more than a prisoner in a gun factory.