The risk is "materially understated", researchers are saying as passwords and critical data can be exfiltrated.
When (and why) does AI coding flip from promising to a security nightmare? Let's look under the coding hood.
TrapDoor spread 34 malicious packages across npm, PyPI, and Crates.io, stealing developer credentials and enabling persistence.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results