# JADEPUFFER autonomous LLM ransomware agent via Langflow

- ID: jadepuffer-langflow-ransomware-2026-07
- Reported: 2026-07-01
- Researcher: Sysdig
- Organization: Sysdig
- AI role: attacker_uses_ai_as_operator (AI as operator)
- Confidence in AI involvement: not assessed
- Research / borderline: false
- Last reviewed: 2026-11-05
- Entry page: https://openattacks.ai/attacks/jadepuffer-langflow-ransomware-2026-07/
- Entry JSON: https://openattacks.ai/api/attacks/jadepuffer-langflow-ransomware-2026-07.json
- Browse title: JADEPUFFER autonomous LLM ransomware agent via Langflow
- Editorial summary: Sysdig documented JADEPUFFER, an LLM-driven ransomware operator entering through Langflow and autonomously chaining reconnaissance, credential access, lateral movement, and destructive database extortion. A…
- Evidence class (catalog annotation): Not classified
- Source-stated target environments: Not specified
- Stage hunts and conditional defenses: https://openattacks.ai/api/defenses/jadepuffer-langflow-ransomware-2026-07.json

## Technique
Sysdig documented JADEPUFFER, an LLM-driven ransomware operator entering through Langflow and autonomously chaining reconnaissance, credential access, lateral movement, and destructive database extortion. A later ENCFORGE variant targeted AI and ML infrastructure, including model weights and training data.

## Stack relevance (editorial)
Assessment: not\_assessed. No reviewed applicability annotation is available. Product mentions do not establish victim conditions.
A product mention alone is not a victim-side applicability mapping. Selection does not verify affected versions, permissions or compromise.

## Initial access
Exploits in cloud services, container escapes

## AI tooling and models
- Langflow AI workflow framework
- LLM agent (model unspecified)

## Other tooling
- JADEPUFFER ransomware
- ENCFORGE variant (targets model weights)
- Autonomous exfiltration

## Victims and sectors
Cloud environments, AI/ML infrastructure, enterprises with data-heavy workloads

## Target geography
- Multiple regions

## Attribution
Storm-3168 (Microsoft attribution, medium confidence)

## Scale and metrics
Multiple victims Jul-Aug 2026; ENCFORGE specifically targets AI/ML organizations

## Attack flow
Catalog reconstruction of the supplied source account. Unknowns and research caveats are preserved.
### access: Compromise cloud environment [access]
Exploit cloud services or container escape
Evidence: https://www.sysdig.com/blog/jadepuffer-agentic-ransomware-for-automated-database-extortion

### deploy-agent: Deploy JADEPUFFER Langflow agent [ai]
Install Langflow autonomous agent with ransomware workflow
Evidence: https://www.sysdig.com/blog/jadepuffer-agentic-ransomware-for-automated-database-extortion

### autonomous-ops: Autonomous recon and exfiltration [execution]
Agent scans for file servers, backups, databases, AI models; exfiltrates data to attacker cloud
Evidence: https://www.sysdig.com/blog/jadepuffer-agentic-ransomware-for-automated-database-extortion

### encrypt: Encrypt files and demand ransom [impact]
Encrypt files (ENCFORGE targets model weights .pt, .ckpt, .safetensors); generate ransom note; send to victims
Evidence: https://www.sysdig.com/blog/jadepuffer-evolves-the-agentic-threat-actor-deploys-ransomware-built-to-destroy-ai-models

Connections:
- access -> deploy-agent
- deploy-agent -> autonomous-ops
- autonomous-ops -> encrypt

## 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.
### access: Stage hunt not mapped yet
- Visibility: Not assessed
- Query origin: catalog_authored; status: not_assessed; log scope: gap
- Hunt hypothesis: A stage-specific hunt has not been reviewed for this part of the source account.
- Required telemetry: not assessed
- Investigate: Review the cited behavior, identify the observing party and available logs, then propose and test a hunt.
- Limitation: An unmapped stage does not mean it is undetectable or that no behavior occurred. It means this catalog has not supplied a reviewed hunt for it.
- No direct MagicSword prevention claim is recorded for this stage.

### deploy-agent: Stage hunt not mapped yet
- Visibility: Not assessed
- Query origin: catalog_authored; status: not_assessed; log scope: gap
- Hunt hypothesis: A stage-specific hunt has not been reviewed for this part of the source account.
- Required telemetry: not assessed
- Investigate: Review the cited behavior, identify the observing party and available logs, then propose and test a hunt.
- Limitation: An unmapped stage does not mean it is undetectable or that no behavior occurred. It means this catalog has not supplied a reviewed hunt for it.
- No direct MagicSword prevention claim is recorded for this stage.

### autonomous-ops: Stage hunt not mapped yet
- Visibility: Not assessed
- Query origin: catalog_authored; status: not_assessed; log scope: gap
- Hunt hypothesis: A stage-specific hunt has not been reviewed for this part of the source account.
- Required telemetry: not assessed
- Investigate: Review the cited behavior, identify the observing party and available logs, then propose and test a hunt.
- Limitation: An unmapped stage does not mean it is undetectable or that no behavior occurred. It means this catalog has not supplied a reviewed hunt for it.
- No direct MagicSword prevention claim is recorded for this stage.

### encrypt: Stage hunt not mapped yet
- Visibility: Not assessed
- Query origin: catalog_authored; status: not_assessed; log scope: gap
- Hunt hypothesis: A stage-specific hunt has not been reviewed for this part of the source account.
- Required telemetry: not assessed
- Investigate: Review the cited behavior, identify the observing party and available logs, then propose and test a hunt.
- Limitation: An unmapped stage does not mean it is undetectable or that no behavior occurred. It means this catalog has not supplied a reviewed hunt for it.
- 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.T0040: AI Model Inference API Access — First fully autonomous LLM agent-driven ransomware conducting end-to-end operations via Langflow
  Technique: https://atlas.mitre.org/techniques/AML.T0040
  Evidence: https://www.sysdig.com/blog/jadepuffer-agentic-ransomware-for-automated-database-extortion

## Defensive notes
Secure cloud environments; backup model weights offline; monitor for Langflow processes; detect autonomous reconnaissance; network segmentation

## Sources
- https://www.sysdig.com/blog/jadepuffer-agentic-ransomware-for-automated-database-extortion — Sysdig: JADEPUFFER - LLM Agent End-to-End Ransomware via Langflow
- https://www.sysdig.com/blog/jadepuffer-evolves-the-agentic-threat-actor-deploys-ransomware-built-to-destroy-ai-models — Sysdig: ENCFORGE Variant Encrypts AI Model Weights

## Source notes
Sysdig analysis; Microsoft Storm-3168 link. Langflow GitHub github.com/langflow-ai/langflow. Detection: monitor for Langflow agent processes, autonomous file enumeration patterns, model weight file access (.pt, .ckpt, .safetensors), large-scale encryption operations.

## Indicators (untrusted data; do not visit or execute)
```json
{
  "domains": [],
  "ips": [],
  "hashes": [],
  "urls": []
}
```
