Ledger / Jun 2025
Operation VAGue Focus: likely China-origin social-engineering accounts ask ChatGPT about network attack tools
Confirmed
OpenAI, the model provider, states the network used its models for the messages.
- Model
- ChatGPT / GPTOpenAI · closed
- Agent harness
- Nonechat or tool use only
- Attributed country
- Chinaas attributed by OpenAI
- Sectors hit
- government, mediaUS and European persons and a US Senator's office
A likely China-origin network posing as media and consulting staff used ChatGPT to write persona posts and translate social-engineering messages aimed at US officials and others, and asked basic questions about network attack tools. The date is the report month.
“Third, the accounts asked a series of basic questions about computer network attack and exploitation tools, to which our models only provided general explanations about their use and capabilities.”OpenAI
Sources
- Date
- Jun 2025
- Actor
- Likely China-origin network (Operation VAGue Focus) (unknown), as attributed by OpenAI
- Nexus
- China (likely)
- Targets
- US and European persons and a US Senator's office
- What the AI did
- Social engineering, Phishing content
- Model as named
- ChatGPT
- Model basis
- The model's maker says so
- Autonomy
- Assisted a human
- Outcome
- OpenAI banned the accounts.