[mdavidn]

A skill is just instructions that the agent can autonomously copy into context. There’s no trust boundary between trusted and untrusted context.

[jychang]

Yeah, this is your fault if you install the skill.

This reads to me as "user installed exe file can upload your data to a server". Um, yes, that's the point?

This seems like this generation's equivalent of "don't open Linkin-Park.mp3.exe from limewire"

[xigoi]

This is the result of anthropomorphizing LLMs. People are thinking “I am giving instructions to a human” and not “I am giving instructions to a computer”.

[Ferret7446]

Humans get phished all the time. The two generals problem predates LLMs.