zlacker

[return to "Malicious skills targeting Claude Code and Moltbot users"]
1. lukev+gc[view] [source] 2026-01-30 19:04:52
>>6mile+(OP)
Watching folks speed-run this whole thing is kind of funny from the outside.

I wonder if anyone with a correct mental model of how LLM agents work (i.e, does not conceptualize them as intelligent entities) has actually granted them any permissions for their own life... personally, I couldn't imagine doing so.

Let alone crypto, the risk of reputational loss for actions performed on my behalf (even just spamming personal or professional contacts) is just too high.

◧◩
2. phillm+se[view] [source] 2026-01-30 19:17:01
>>lukev+gc
i can't imagine running these things outside of a vm and it's bizarre to see how many people yolo it
◧◩◪
3. edmund+1o[view] [source] 2026-01-30 20:10:16
>>phillm+se
I installed it on a spare computer, physically separated. My bigger concern is giving it access to accounts online, without those however it is not very cool.
[go to top]