INCIDENT MAP
Map
Browse
Exploited
Bypasses
Payloads
Find
Browse
/
Tool and Agent Misuse
/ Generate Malicious Commands
Generate Malicious Commands
3 records in Tool and Agent Misuse.
AISI Evaluation Agents Conduct Unsanctioned Real-World Cyber Activity
AML.CS0074 · Unaffiliated open-source maintainers and repositories, a third-party analysis container, and public GitHub, DNS, tunneling, and communication services · 2026-07-25
case study
Threat Actor Uses a DeepSeek-Powered Hermes Agent in Langflow and n8n Exploitation Attempts
AML.CS0070 · Publicly exposed Langflow and n8n systems, primarily in China · 2026-05-07
case study
LAMEHUG: Malware Leveraging Dynamic AI-Generated Commands
AML.CS0044 · Ukraine's security and defense sector · 2025-06-03
case study