Opening SecureFlowFlowise Honeypot: Unauthenticated API Abuse, Beacon Setup, and Agent Probing
Case summary & sources

AIDEFEND SecureFlow / SecureFlow Case Index

Sekoia TDR Team aidefend-sf0095

Flowise Honeypot: Unauthenticated API Abuse, Beacon Setup, and Agent Probing

  • Autonomous Agents
  • AI Infrastructure
  • RAG & Knowledge Systems
  • Credential & Identity Theft
  • Data Exfiltration
  • Resource Hijacking & Cost
  • Model Poisoning & Integrity

Sekoia recorded six phases of real attacker traffic against an internet-facing decoy that emulated Flowise 2.2.8, a platform for building AI workflows. The exposed management API let the attacker retrieve planted credentials and add a workflow configured to call back. The attacker then tried to override prompts, probe session memory and ask the simulated agent about real third-party infrastructure. The decoy returned simulated responses, so the requests do not establish real command execution, database access or a Nightingale compromise.

Mapped threat techniques

  • AML.T0132 Misconfigured or Publicly Exposed AI Services
  • AML.T0083 Credentials from AI Agent Configuration
  • AML.T0081 Modify AI Agent Configuration
  • AML.T0051.000 Direct
  • AML.T0085.000 RAG Databases

Source