Article
I hacked Perplexity Computer and got unlimited Claude Code
One prompt. Three shell commands. I used their own AI to hack itself. This is a class of bug that probably exists in every multi-agent AI product shipping today. And the fix is a design pattern that...
Readers added context they thought people might want to knowReaders added context
This security audit is factually inaccurate. It does not provide any network information regarding the "arbitrary ip" used to access the proxy token outside of the perplexity computer interface. Denis Yarats confirmed the token is not hidden by choice of the service provider. x.com/denisyarats/st…
Context is written by people who use X, and appears when rated helpful by others. Find out more.