Operation “ScopeCreep”: Russian-speaking malware development

This case study was originally published in OpenAI’s June 2025⁠(opens in a new window) report.

Actor

We banned a cluster of ChatGPT accounts that appeared to be operated by a Russian-speaking threat actor. This actor used our models to assist with developing and refining Windows malware, debugging code across multiple languages, and setting up their command-and-control infrastructure.

The actor demonstrated knowledge of Windows internals and exhibited some operational security behaviors. Based on the operation’s focus on using a trojanized “crosshair” gaming tool and its stealthy tactics, we have dubbed it “ScopeCreep.”

Behavior

This threat actor had a notable approach to operational security. They utilized temporary email addresses to sign up for ChatGPT accounts, limiting each ChatGPT account to one conversation about making one incremental improvement to their code. They then abandoned the original account and created a new one.

The actor distributed the ScopeCreep malware through a publicly available code repository that impersonated a legitimate and popular crosshair overlay tool (Crosshair-X) for video games. Unsuspecting users who downloaded and ran the malicious version would initiate the malware loader on their system, resulting in additional malicious files being downloaded from attacker infrastructure and executed.

From there, the malware was designed to initiate a multi-stage process to escalate privileges, establish stealthy persistence, notify the threat actor, and exfiltrate sensitive data while evading detection.

The threat actor utilized our model to assist in developing the malware iteratively, by continually requesting ChatGPT to implement further specific features. ScopeCreep showcased a range of techniques across delivery, execution, evasion, and exfiltration, including:

Completions

Representative examples of these activities can be mapped to the LLM ATT&CK framework as follows: