# PROMPTLOCK LLM-generated Lua ransomware PoC

- ID: promptlock-gtig-eset-2025
- Reported: 2025-11-05
- Researcher: Google GTIG; ESET
- Organization: Google GTIG / ESET
- AI role: llm_generated_malware (LLM-generated malware)
- Confidence in AI involvement: not assessed
- Research / borderline: true
- Last reviewed: 2026-10-20
- Entry page: https://openattacks.ai/attacks/promptlock-gtig-eset-2025/
- Entry JSON: https://openattacks.ai/api/attacks/promptlock-gtig-eset-2025.json
- Browse title: PROMPTLOCK LLM-generated Lua ransomware (PoC)
- Editorial summary: A Go ransomware proof of concept uses an LLM to generate Lua scripts for recon, data theft and encryption on Windows and Linux. It has not been reported as an active campaign.
- Evidence class (catalog annotation): Research demonstration
- Source-stated target environments: Windows; Linux
- Stage hunts and conditional defenses: https://openattacks.ai/api/defenses/promptlock-gtig-eset-2025.json

## Evidence qualification
Proof of concept / experimental; not reported as active campaign.

## Technique
Cross-platform Go ransomware PoC that uses an LLM to dynamically generate and execute malicious Lua for filesystem recon, exfil, and encryption on Windows and Linux. ESET described related research as first known AI-written ransomware using local gpt-oss:20b.

## Stack relevance (editorial)
Assessment: mapped. Editorial applicability reviewed against the catalog source account; not a scan or independent incident verification.
First action: Review interpreter execution and access to files that an untrusted program could encrypt.
- Relationship: environment; tools: no specific product; OS scope: windows, linux; requires existing MCP connections: false.
  Relevance: The PoC demonstrates LLM-generated Lua executing on Windows or Linux.
  Condition to check: This is experimental research, not a reported active ransomware campaign.
  Evidence: https://cloud.google.com/blog/topics/threat-intelligence/threat-actor-usage-of-ai-tools/ ; https://www.eset.com/blog/en/business-topics/threat-landscape/the-first-known-ai-written-ransomware/
A product mention alone is not a victim-side applicability mapping. Selection does not verify affected versions, permissions or compromise.

## Initial access
unknown

## AI tooling and models
- LLM at runtime
- Lua script generation
- [gpt-oss:20b](https://github.com/openai/gpt-oss) (ESET write-up)

## Other tooling
- [Go](https://github.com/golang/go)

## Victims and sectors
unknown

## Target geography
- unknown

## Attribution
unknown

## Scale and metrics
unknown

## Attack flow
Catalog reconstruction of the supplied source account. Unknowns and research caveats are preserved.
### step-1: PoC starts in a research setting [unknown]
This entry is a ransomware proof of concept, not a confirmed victim campaign.
Evidence: https://cloud.google.com/blog/topics/threat-intelligence/threat-actor-usage-of-ai-tools/ ; https://www.eset.com/blog/en/business-topics/threat-landscape/the-first-known-ai-written-ransomware/

### step-2: LLM generates Lua at runtime [ai]
A Go program requests filesystem-related malicious scripts.
Evidence: https://cloud.google.com/blog/topics/threat-intelligence/threat-actor-usage-of-ai-tools/ ; https://www.eset.com/blog/en/business-topics/threat-landscape/the-first-known-ai-written-ransomware/

### step-3: Generated Lua is executed [execution]
The research describes reconnaissance, exfiltration and encryption logic.
Evidence: https://cloud.google.com/blog/topics/threat-intelligence/threat-actor-usage-of-ai-tools/ ; https://www.eset.com/blog/en/business-topics/threat-landscape/the-first-known-ai-written-ransomware/

### step-4: Research demonstrates ransomware behavior [impact]
The PoC demonstrates potential Windows and Linux impact.
Evidence: https://cloud.google.com/blog/topics/threat-intelligence/threat-actor-usage-of-ai-tools/ ; https://www.eset.com/blog/en/business-topics/threat-landscape/the-first-known-ai-written-ransomware/

Connections:
- step-1 -> step-2
- step-2 -> step-3
- step-3 -> step-4

## Stage defense and hunting recommendations
Editorial recommendations, not validated coverage. Source-controlled query starters are drafts. Custom-schema examples require telemetry collection and field mapping; absence of a mapping means not assessed. MagicSword policy opportunities require managed Windows scope and enforcement.
### step-1: No source-backed runtime hunt yet
- Visibility: Not established
- Query origin: catalog_authored; status: not_applicable; log scope: gap
- Hunt hypothesis: The supplied account does not establish a deployed victim-side behavior for this stage.
- Required telemetry: not assessed
- Investigate: Obtain a source-backed procedure and identify which party could observe it before drafting a detection.
- Limitation: Marketing claims, unknown steps and unconfirmed deployments are not detection coverage. No rule is generated for this stage.
- Qualification: The supplied account leaves this stage unestablished. Obtain a source-backed procedure before proposing a runtime query.
- No direct MagicSword prevention claim is recorded for this stage.

### step-2: Unexpected process → model service
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/model-network.sigma.yml
- KQL query download: /api/detections/model-network.kql
- SPL query download: /api/detections/model-network.spl
- Hunt hypothesis: An unexpected script, implant or local model client communicates with a model service near command execution, collection or file modification.
- Required telemetry: Per-process network / DNS records; AI-service request logs where available; Process and file behavior on the calling host
- Investigate: Join the network connection to the process tree and the actions before and after the response.
- Investigate: Compare with approved AI integrations; inspect local model listeners for PoCs that do not use a hosted API.
- Limitation: Connecting to a legitimate model domain does not establish malicious use or reveal returned code. Local / in-process models can evade network-only hunts.
- No direct MagicSword prevention claim is recorded for this stage.

### step-3: Unexpected agent tool use
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/agent-tools.sigma.yml
- KQL query download: /api/detections/agent-tools.kql
- SPL query download: /api/detections/agent-tools.spl
- Hunt hypothesis: Untrusted content or a changed tool definition precedes a file read, command, or remote call outside the user's intended task.
- Required telemetry: Agent tool-call audit records with session / tool / destination; Tool-definition and approval changes; Endpoint process, file-access and network evidence where available
- Investigate: Join input provenance, tool descriptions and calls by session ID and compare the action to the approved task.
- Investigate: Inspect child processes and destinations; record whether execution was in-process, local, or through a remote SaaS connector.
- Limitation: Process logs cannot recover model intent. Remote connectors and in-process interpreters may produce no local child process. Prompt content alone is not a reliable signature.
- Qualification: The Go process embeds a Lua execution path; child-process hunts alone will miss in-process Lua.
- No direct MagicSword prevention claim is recorded for this stage.

### step-4: Collection / encryption behavior
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/impact.sigma.yml
- KQL query download: /api/detections/impact.kql
- SPL query download: /api/detections/impact.spl
- Hunt hypothesis: A process rapidly enumerates or modifies sensitive files and is followed by encryption, export or a ransom-related artifact.
- Required telemetry: File-operation rates and process attribution; Ransomware / DLP behavior alerts; Canary files and recovery / backup audit
- Investigate: Correlate file bursts, extension changes and outbound transfer to the same process and identity.
- Investigate: Validate against bulk backup / archiving activity and preserve the research-only qualification of a PoC.
- Limitation: A file-write burst is not proof of ransomware; in-process interpreters may not spawn a separate executable.
- No direct MagicSword prevention claim is recorded for this stage.


## MITRE ATLAS
Mappings are catalog annotations based on described behavior, not assignments or endorsements by MITRE.
- AML.T0102: Generate Malicious Commands — The ransomware proof of concept generates Lua scripts at runtime.
  Technique: https://atlas.mitre.org/techniques/AML.T0102
  Evidence: https://cloud.google.com/blog/topics/threat-intelligence/threat-actor-usage-of-ai-tools/ ; https://www.eset.com/blog/en/business-topics/threat-landscape/the-first-known-ai-written-ransomware/

## Defensive notes
Treat unexpected local LLM + script generation as high signal; ransomware fundamentals unchanged

## Sources
- https://cloud.google.com/blog/topics/threat-intelligence/threat-actor-usage-of-ai-tools/
- https://www.eset.com/blog/en/business-topics/threat-landscape/the-first-known-ai-written-ransomware/
