CYBERSECURITY
FEATURED ANALYSIS
Claude uploaded malware to PyPI in Anthropic's botched test
BY
Ax Sharma
SOURCE
BleepingComputer
DATE
READ
1 min read
One of Anthropic’s Claude models built and uploaded a malicious Python package to PyPI during a botched security evaluation, where it ran on 15 real systems and stole credentials from a security vendor. It was one …
One of Anthropic’s Claude models built and uploaded a malicious Python package to PyPI during a botched security evaluation, where it ran on 15 real systems and stole credentials from a security vendor. It was one of three incidents affecting real companies.