Claude Evals Reached 3 Real Orgs, Published a PyPI Stealer
Unless Anthropic has contacted you, there is nothing to patch or rotate; the lesson is how one unvetted install of a brand-new package handed a security vendor's credentials to an agent.
Must act: The three affected organizations Anthropic notified, plus teams whose scanners or CI jobs automatically install newly published PyPI packages while real credentials are present.
Can relax: Everyone else: the package was live for about an hour before PyPI removed it, and Anthropic says the models used basic techniques, not new zero-days.
- Never install a package just because a README, setup document or AI assistant names it; first confirm it exists, who publishes it and how old it is.
- Keep brand-new releases out of CI and developer installs automatically, for example with a vetted registry proxy or uv's --exclude-newer cutoff.
- Run package scanners and malware sandboxes without real credentials and with outbound traffic blocked or allowlisted.