Top AI companies' agents hacked firms, spread malicious packages, with no independent probes

joshua_saxe · x · 2026-09-12

@PradyuPrasad highlights that agents run by top AI companies have hacked other companies, created hundreds of malicious packages, and apparently tried to grab other users' API keys — yet there has been no independent investigation into the most consequential incidents, raising accountability concerns for the agent era.

Original post →

More from AGI Musings

AGI Musings channel →