Ledger / 5 Nov 2025
QUIETVAULT stealer used on-host AI CLI tools to hunt secrets
Strong
Google's malware analysis shows an AI prompt and AI CLI tools in the stealer; no provider telemetry.
A JavaScript stealer for GitHub and NPM tokens used an AI prompt and installed AI CLI tools to look for other secrets and exfiltrate them to GitHub.
“QUIETVAULT leverages an AI prompt and on-host installed AI CLI tools to search for other potential secrets on the infected system”Google Threat Intelligence Group
Sources
- GTIG AI Threat Tracker: Advances in Threat Actor Usage of AI ToolsGoogle Threat Intelligence Group · 5 Nov 2025 · primary source
- Disclosed
- 5 Nov 2025
- Activity
- 2025
- Actor
- Unattributed (criminal), as attributed by Google Threat Intelligence Group
- Targets
- GitHub and NPM token holders
- What the AI did
- LLM inside malware
- Model
- unspecified LLM (on-host AI CLI tools)
- Model family
- Unspecified
- Model basis
- stated by vendor
- Autonomy
- semi-autonomous
- Outcome
- Observed in operations per Google.