Level 4. Critical control failure
JadePuffer ransomware used AI agent to automate entire attack
- Developer
- Not established
- Model
- Not established
- When it happened
- July 1, 2026
- When it was disclosed
- Not established
- How well it is stood up
- Not verified yet
- What caused it
- Not established
- Where it stands now
- Not established
What happened
Reported by bleepingcomputer.com. Listed here with a link to their report. Nobody on this side has checked it against that report, so it carries no level and this is not our account of what happened.
Our assessment
- Actual
- 4 of 5Critical control failure
- Potential
- 4 of 5Critical control failure
Serious loss of control, dangerous autonomous behaviour, or a credible path to severe harm. The potential level is what the behaviour demonstrated here could credibly have led to, judged from the same evidence.
This level rests on news reports. The developer has not confirmed it here.
Why this level
- Sustained harmful autonomous behaviour. Argues for level 4
- Major compromise of an external system. Argues for level 4
- A security boundary was crossed. Argues for level 3
- An external system was affected. Argues for level 3
- Sensitive data was reachable. Argues for a potential level of 3
- The system acted autonomously. Argues for a potential level of 3
What is established, and what is not
Confirmed
Major compromise of an external system
According to cloud security company Sysdig, JadePuffer used an autonomous AI agent for reconnaissance on the target, to steal credentials, move laterally, establish persistence, escalate privileges, and to encrypt data.
JadePuffer ransomware used AI agent to automate entire attack
Reported, not confirmed
The system acted autonomously
According to cloud security company Sysdig, JadePuffer used an autonomous AI agent for reconnaissance on the target, to steal credentials, move laterally, establish persistence, escalate privileges, and to encrypt data.
JadePuffer ransomware used AI agent to automate entire attackAn external system was affected
According to the researchers, JadePuffer encrypted 1,342 Nacos service configuration items before deleting the originals.
JadePuffer ransomware used AI agent to automate entire attackA security boundary was crossed
JadePuffer gained initial access to the target by exploiting CVE-2025-3248, an unauthenticated remote code execution vulnerability in Langflow, a popular open-source framework used for building LLM apps.
JadePuffer ransomware used AI agent to automate entire attackSensitive data was reachable
After obtaining code execution through CVE-2025-3248, the AI agent dumped Langflow's PostgreSQL database, collected host information, searched for environment variables and sensitive files, retrieved credentials, and enumerated a MinIO object store.
JadePuffer ransomware used AI agent to automate entire attackSustained harmful autonomous behaviour
An LLM-driven agent chained reconnaissance, credential theft, lateral movement, and database destruction on its own, encrypting 1,342 config items.
Sysdig documented JadePuffer, the first ransomware operation run end to end by an AI agent
Checked, and did not happen
Nothing here was checked and ruled out.
Not confirmed
Nothing is outstanding.
Where this came from
The original report
JadePuffer ransomware used AI agent to automate entire attackA structured incident database · read September 18, 2026
AI Failure Index (CC-BY-4.0 data fields)Where we first saw it · read September 19, 2026
Sysdig documented JadePuffer, the first ransomware operation run end to end by an AI agentWhere we first saw it
JadePuffer ransomware used AI agent to automate entire attackWhere we first saw it
JadePuffer: The First Successful LLM-Driven Ransomware AttackWhere we first saw it
AI agent exploits Langflow in first fully autonomous ransomware attack
The reports above are other people’s. The levels are ours, worked out under our published rules. No organisation that reported this assigned our number, and none of it is legal advice.
Something here is wrong? Tell us. Send us a source we can open, and a person will read it.