Google GTIG AI Threat Tracker: agentic setup harvested cloud credentials in under six hours
GTIG documented a Mandiant-investigated intrusion where an autonomous multi-agent setup ran scanning, credential harvesting and IP rotation with little human input, alongside TeamPCP malware targeting AI…
What happened
GTIG documented a Mandiant-investigated intrusion where an autonomous multi-agent setup ran scanning, credential harvesting and IP rotation with little human input, alongside TeamPCP malware targeting AI tooling.
How it happened
Read the flow as text & sources
A summary diagram derived from the entry fields, not a verified detailed sequence. Unknown steps remain explicit; an edge describes the reported relationship between steps.
- 01 · Reported initial access
unknown
Source for step 1 - 02 · Reported activity
GTIG documented a Mandiant-investigated intrusion where an autonomous multi-agent setup ran scanning, credential harvesting and IP rotation with little human input, alongside TeamPCP malware targeting AI tooling.
Source for step 2 - 03 · AI involvement
Unnamed AI coding chatbot used as agent · AI coding tool configs (.claude, .cursor, .vscode) · LLM-based code reviewers targeted by embedded prompts
Source for step 3
Why it matters
Reported impact: the cited report does not establish a confirmed victim outcome; reported targets include Technology and AI companies; Multiple sectors; applicability to your setup has not been assessed, so verify affected versions, permissions, and configuration in the original report.
What you can do
Protection & prevention
Prevention guidance has not been recorded for this entry. Review the original report for available mitigations.
Catalog defensive guidance based on the reported behavior. Confirm scope and current mitigations in the original source.
Technical detailsTooling, impact
Attack context
- AI's role
- AI as operator
- Additional role
- LLM-generated malware
Tooling as reported
AI products, models and artifacts
- Unnamed AI coding chatbot used as agent
- AI coding tool configs (.claude, .cursor, .vscode)
- LLM-based code reviewers targeted by embedded prompts
Targets and reported impact
- Targets / sectors
- Technology and AI companies; Multiple sectors
Target geography was not captured by the Notion feed. Actor attribution is not used as a victim location.
Reported attribution
Unnamed financially motivated actor; UNC6780 (TeamPCP); unknown 'Recon' dashboard operator
Structured attribution
- Motivation
- cybercrime
Sources & research credit
2 sourcesResearch by unknown · Google Threat Intelligence Group
Imported from the AI Threat Watch Notion feed (an automated daily scan); not yet editorially reviewed. Feed severity: High. Feed novelty: Evolution.
Record & downloads
- Source record name
- Google GTIG AI Threat Tracker: agentic setup harvested cloud credentials in under six hours
- Entry ID
- google-gtig-ai-threat-tracker-agentic-2026-09
- Category
- adversary-use-of-ai
- AI involvement confidence
- vendor-asserted