Hacker slips malicious 'wiping' command into Amazon's Q AI coding assistant - and devs are worried
Briefly

A recent incident involved a hacker compromising Amazon's Q AI coding agent by submitting a malicious pull request on GitHub, which included instructed commands that could potentially erase local files and dismantle cloud infrastructure. Although the attacker downplayed the likelihood of large-scale data destruction, it raised serious concerns regarding the security of AI tools. The update that included these commands passed Amazon's verification process, leading to widespread criticism of the incident. Amazon Q's role is to streamline coding and deployment processes in AWS, making this breach particularly troubling for developers.
A hacker introduced destructive wiping commands in Amazon's "Q" AI coding agent through a malicious pull request, raising concerns across developer communities.
The attacker claimed the actual risk of large-scale data wiping was low, but highlighted that their access could have led to much worse outcomes.
The troubling incident revealed that a dangerous update had passed Amazon's verification process and made its way into a public release.
Amazon Q is part of AWS's AI developers suite, designed to enhance efficiency in coding, testing, and deployment.
Read at ZDNET
[
|
]