Fed up with vibe coders, dev sneaks data-nuking prompt injection into their code
Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.
Directly relevant to AI coding agents and prompt injection, highly actionable for developers.
Johannes Link added a prompt injection to jqwik 1.10.0, a JUnit 5 test engine, that instructs AI coding agents to delete all jqwik tests and code, using ANSI escapes to mask the command from human terminal viewers. The injection triggered backlash after developer Ramon Batllet flagged it on GitHub, noting that vulnerable agents could destroy user work with no warning or opt-out. Link later disclosed the injection in release notes, defending the move against "vibe coding" and AI agent misuse, while facing legal threats.
- Audit your AI coding agents' behavior against prompt injection attacks when ingesting third-party dependencies, and consider adding runtime protections to prevent destructive commands from being executed.
This event exposes a new supply-chain risk in agent-driven development: prompt injections embedded in open-source libraries can cause AI coding agents to execute destructive actions, directly impacting the safety and reliability of the automated workflows you design.
Dan Goodin — Dan Goodin is Senior Security Editor at Ars Technica, where he oversees coverage of malware, computer espionage, botnets, hardware hacking, encryption, and passwords. A journalist with more than 25 years experience, he has been chronicling the...