Mandiant AI risk report details hijacked coding-assistant session that spread Shai-Hulud worm
Mandiant's special report gives incident-response case studies of attackers hijacking AI coding sessions, subverting assistant CLI hooks and fielding malware that uses embedded AI models to evade EDR.
What happened
Mandiant's special report gives incident-response case studies of attackers hijacking AI coding sessions, subverting assistant CLI hooks and fielding malware that uses embedded AI models to evade EDR.
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
Mandiant's special report gives incident-response case studies of attackers hijacking AI coding sessions, subverting assistant CLI hooks and fielding malware that uses embedded AI models to evade EDR.
Source for step 2 - 03 · AI involvement
Developer AI coding assistant sessions, internal AI repositories and assistant CLI hooks, embedded lightweight AI models in malware
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; Finance; 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
- Developer AI coding assistant sessions, internal AI repositories and assistant CLI hooks, embedded lightweight AI models in malware
Targets and reported impact
- Targets / sectors
- Technology and AI companies; Finance; Multiple sectors
Target geography was not captured by the Notion feed. Actor attribution is not used as a victim location.
Reported attribution
Unnamed; UNC6780 (TeamPCP) referenced
Structured attribution
- Motivation
- cybercrime
Sources & research credit
2 sourcesResearch by unknown · Google Cloud / Mandiant
Imported from the AI Threat Watch Notion feed (an automated daily scan); not yet editorially reviewed. Feed severity: High. Feed novelty: New TTP.
Record & downloads
- Source record name
- Mandiant AI risk report details hijacked coding-assistant session that spread Shai-Hulud worm
- Entry ID
- mandiant-ai-risk-report-details-hijacked-2026-09
- Category
- adversary-use-of-ai
- AI involvement confidence
- vendor-asserted