Ledger / Jun 2026
JadePuffer: LLM agent runs an entire extortion operation from Langflow exploit to data destruction
Confirmed
Sysdig's analysis shows self-narrating LLM payloads; I verified it through The Register's report, not Sysdig's own page.
Sysdig says an LLM, not a human, drove the intrusion: exploit CVE-2025-3248, steal credentials, persist, attack the database and encrypt. It retried failed steps in real time. Primary Sysdig URL was not verified.
“gained initial access to an internet-facing Langflow instance”The Register
Sources
- Smooth AI criminal drives 'first' end-to-end agentic ransomware attackThe Register · 2 Jul 2026 · secondary source
- Date
- Jun 2026
- Disclosed
- 2 Jul 2026
- Actor
- JadePuffer (Sysdig name) (criminal), as attributed by The Register
- Targets
- Internet-facing Langflow instance, then an exposed MySQL and Alibaba Nacos production server
- What the AI did
- Agentic intrusion, Exploit dev, Ops automation
- Model
- unspecified LLM
- Model family
- Unspecified
- Model basis
- unknown
- Autonomy
- autonomous
- Outcome
- 1,342 Nacos configuration items encrypted with an unrecoverable ephemeral key; ransom note left; data not recoverable even if paid.