PROMPTFLUX Gemini-powered self-modifying VBScript dropper
An experimental VBScript dropper queries Gemini for antivirus-evasion rewrites. The analyzed self-update function was commented out, so active self-rewriting is not established.
What happened
VBScript dropper with decoy installer; 'Thinking Robot' module POSTs to Gemini API (gemini-1.5-flash-latest) with hard-coded key asking for VBScript AV-evasion rewrites; intends Startup persistence and removable-drive spread. Self-update function commented out in analyzed samples.
Experimental LLM-augmented malware (self-obfuscation via Gemini API)
How it happened
Read the flow as text & sources
A catalog reconstruction of the supplied source account. GTIG classifies as experimental/dev; incomplete features; no demonstrated ability to compromise victims.
- 01 · Initial delivery is not established
The analyzed VBScript includes a decoy installer, but the initial route is unknown.
Source for step 1 - 02 · Thinking Robot queries Gemini
A hard-coded key supports requests for VBScript evasion rewrites.
Hunt: An unexpected script, implant or local model client communicates with a model service near command execution, collection or file modification.
Connecting to a legitimate model domain does not establish malicious use or reveal returned code. Local / in-process models can evade network-only hunts.
Source for step 2 - 03 · Dropper contains a rewrite workflow
The analyzed sample contains code for self-modification.
Hunt: A script host or shell runs encoded content, a remote URL, or inline script syntax, then downloads or launches a payload.
Encoded commands and remote administration can be legitimate. This does not cover every script host, in-process execution, or non-Windows branch.
MagicSword policy opportunity · Windows VBScript execution. The analyzed sample's self-update function was commented out; blocking it is not proof of stopping an active self-rewrite chain.
Source for step 3 - 04 · Self-update is commented out
Startup persistence and removable-drive spread are intended behavior; the analyzed rewrite function was not active.
Source for step 4
Why it matters
Reported impact: Experimental; Google disabled associated assets; using the named AI products does not by itself establish exposure.
What you can do
Protection & prevention
Monitor Gemini API keys embedded in scripts; block unexpected generative API from endpoints
Catalog defensive guidance based on the reported behavior. Confirm scope and current mitigations in the original source.
Detection queries
Draft query starters grouped by the attack stages where they apply.
Start with the logs you collect. Each hunt identifies its required visibility, field mapping and limits. Queries are catalog-authored drafts using reusable behavior profiles; test with known activity and your normal baseline before alerting.
02Thinking Robot queries GeminiUnexpected process → model serviceCustom schema · Draft
A hard-coded key supports requests for VBScript evasion rewrites.
What to look for
An unexpected script, implant or local model client communicates with a model service near command execution, collection or file modification.
Visibility: Defender-side logs where collected
Required logs
- Per-process network / DNS records
- AI-service request logs where available
- Process and file behavior on the calling host
Coverage limit. Connecting to a legitimate model domain does not establish malicious use or reveal returned code. Local / in-process models can evade network-only hunts.
Custom-schema candidates, not out-of-box detectors. Map your application / cloud / platform logs to EventType, Actor, Asset, Action, Target and CorrelationId. KQL uses a custom OpenAttacksAudit_CL table; SPL uses openattacks:audit. EventType values are proposed normalization names, not native vendor event names. Correlation and environment-specific alert logic remain to be built.
Sigma
title: Hunt - Unexpected process → model service
id: 8560daf7-ecd1-4f2b-ad09-b794bb56a394
status: experimental
description: An unexpected script, implant or local model client communicates
with a model service near command execution, collection or file modification.
author: MagicSword OpenAttacks catalog
date: 2026-10-23
falsepositives:
- Authorized activity matching this broad hunt; baseline and investigate
before alerting.
level: low
logsource:
category: application
product: openattacks_audit
definition: Custom normalized audit schema; map EventType, Actor, Asset, Action,
Target and CorrelationId from the required source logs first.
detection:
selection:
EventType:
- model.connection
- model.invoke
condition: selection
KQL
// SCHEMA TEMPLATE: create/map this custom table before use; not a built-in Sentinel table.
// OpenAttacksAudit_CL: TimeGenerated(datetime), EventType/Actor/Asset/Action/Target/CorrelationId(string).
// Selects candidates only. Apply the stage hypothesis and correlation steps before alerting.
OpenAttacksAudit_CL
| where TimeGenerated > ago(7d)
| where EventType in ("model.connection", "model.invoke")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated descSPL
sourcetype="openattacks:audit"
EventType IN ("model.connection", "model.invoke")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _timeInvestigation steps
- Join the network connection to the process tree and the actions before and after the response.
- Compare with approved AI integrations; inspect local model listeners for PoCs that do not use a hosted API.
03Dropper contains a rewrite workflowSuspicious Windows script executionNative logs · Draft
The analyzed sample contains code for self-modification.
What to look for
A script host or shell runs encoded content, a remote URL, or inline script syntax, then downloads or launches a payload.
Visibility: Defender-side logs where collected
Required logs
- Windows process creation: Sysmon Event 1 or Defender DeviceProcessEvents
- PowerShell script-block logging when enabled
- Download / network and installer events
Coverage limit. Encoded commands and remote administration can be legitimate. This does not cover every script host, in-process execution, or non-Windows branch.
Windows process candidates. Sigma uses normalized process_creation fields; KQL requires Defender for Endpoint; SPL requires the Sysmon XML sourcetype. Tune collectors, fields and baselines before use.
Sigma
title: Hunt - Suspicious Windows script execution
id: 2bb88802-9f03-4d99-a192-fe44c9484e8b
status: experimental
description: A script host or shell runs encoded content, a remote URL, or
inline script syntax, then downloads or launches a payload.
author: MagicSword OpenAttacks catalog
date: 2026-10-23
falsepositives:
- Authorized activity matching this broad hunt; baseline and investigate
before alerting.
level: low
logsource:
category: process_creation
product: windows
detection:
selection:
Image|endswith:
- \powershell.exe
- \pwsh.exe
- \mshta.exe
- \wscript.exe
- \cscript.exe
CommandLine|contains:
- -enc
- http
- FromBase64String
- "javascript:"
- "vbscript:"
condition: selection
KQL
// Draft hunt; requires Defender for Endpoint process telemetry for this OS.
DeviceProcessEvents
| where Timestamp > ago(7d)
| where FileName in~ ("powershell.exe", "pwsh.exe", "mshta.exe", "wscript.exe", "cscript.exe")
| where ProcessCommandLine contains "-enc" or ProcessCommandLine contains "http" or ProcessCommandLine contains "FromBase64String" or ProcessCommandLine contains "javascript:" or ProcessCommandLine contains "vbscript:"
| project Timestamp, DeviceName, AccountName, FileName, ProcessCommandLine, InitiatingProcessFileName, InitiatingProcessCommandLine, SHA1
| order by Timestamp descSPL
sourcetype="XmlWinEventLog:Microsoft-Windows-Sysmon/Operational" EventCode=1
Image IN ("*\\powershell.exe", "*\\pwsh.exe", "*\\mshta.exe", "*\\wscript.exe", "*\\cscript.exe")
CommandLine IN ("*-enc*", "*http*", "*FromBase64String*", "*javascript:*", "*vbscript:*")
| table _time host User Image CommandLine ParentImage ParentCommandLine
| sort - _timeInvestigation steps
- Follow the parent and child process tree and recover the script or URL from logs without executing it.
- Correlate the payload's signer/hash, persistence, and network activity; baseline approved automation.
Technical detailsTooling, impact & MITRE ATLAS
Attack context
- AI's role
- LLM-generated malware
Tooling as reported
AI products, models and artifacts
Other tooling
- VBScript
- Startup folder persistence
Targets and reported impact
- Reported scale / exposure
- Experimental; Google disabled associated assets
Reported attribution
unattributed; financially motivated lure filenames suggested
Structured attribution
- Actor
- unattributed
- Motivation
- financially-motivated
Detection rules
- Review attack-specific indicatorsGUIDANCE
Monitor for the techniques described in PROMPTFLUX Gemini API self-modifying VBScript dropper. Refer to sources for specific IOCs and TTPs.
Source defensive notes
Monitor Gemini API keys embedded in scripts; block unexpected generative API from endpoints
MITRE ATLAS
AI-specific catalog annotations based on the reported behavior; these are not MITRE case-study assignments.
A dropper requests generated VBScript rewrites; the analyzed self-update routine is commented out. Source
Sources & research credit
1 sourceResearch by Google Threat Intelligence Group · Google GTIG
Record & downloads
- Source record name
- PROMPTFLUX Gemini API self-modifying VBScript dropper
- Entry ID
- promptflux-gtig-2025-06
- Catalog review
- October 20, 2026
- Category
- adversary-use-of-ai
- AI involvement confidence
- unverified