An LLM-driven operator ran a database extortion campaign end to end

Sysdig's threat research team documented an extortion operation it describes as driven end to end by a large language model. It entered through an internet-facing Langflow instance (CVE-2025-3248), pivoted to the intended target, and ran a destructive database-extortion playbook against production data.

Source: Sysdig Threat Research Team, JADEPUFFER (July 2026)↗

Failure modes it illustrates

• FM-03Insecure tool use

  The tools an agent calls become the attack surface: unvalidated inputs, unauthenticated tool servers, or tool descriptions that themselves carry malicious instructions.

• FM-06Cascading actions

  Multi-step and multi-agent workflows propagate one early error through every downstream step: a chain reaction at machine speed.