Knowledge Base Regulation Tracker Standards & Frameworks OSS Directory AI Incident Database Research Paper Library Case Studies Society Articles News Jobs About Charter Sign inBecome a Member
Home/AI Incident Database/Malicious prompt inserted into a released version of an AI coding extension instructs it to wipe systems

Malicious prompt inserted into a released version of an AI coding extension instructs it to wipe systems

An attacker submitted a pull request that added a prompt telling the assistant to clean a system to a near-factory state and delete cloud resources; it shipped in an official release, and the attacker said the goal was to expose weak release security.

Severity: MediumSupply chainPrompt as codeVS Code extensionRelease integrity

Contribute

Spot an error, or know a record we should add? Members can propose additions and submit corrections.