A developer has added malicious instructions to the jqwik Java testing application, which could result in the deletion of tests and code by AI coding agents. This action, described as prompt injection, exploits vulnerabilities in AI systems.
Our neutral summary
A developer has added malicious instructions to the jqwik Java testing application, which could result in the deletion of tests and code by AI coding agents. This action, described as prompt injection, exploits vulnerabilities in AI systems.
The reporting belongs to Ars Technica; we don't reproduce it.
No note attached
on this article.
Fed up with vibe coders, dev sneaks data-nuking prompt injection into their code
Developer Implements Malicious Code in Open Source Java Testing App