Executive Summary
Unit 42 says a Chinese-speaking actor used DeepSeek through the open-source Hermes Agent framework to attack autonomously: after one Telegram instruction, the agent found internet-facing systems and chose public exploits with no further operator input.
What Happened
Palo Alto Networks' Unit 42 says a Chinese-speaking threat actor used DeepSeek through the open-source Hermes Agent framework to launch attacks autonomously. After an initial Telegram instruction, the agent found internet-facing systems and selected public exploits. The researchers recovered no further operator input in the session. The operator, tracked through the aliases knaithe and KnYuan,
Affected Products
- DeepSeek
- Hermes Agent
Vulnerability / Attack Technique
Autonomous agent-driven attacks from a single instruction
Technical Mechanism
The operator sent one instruction via Telegram; the agent scanned for targets and selected exploits on its own.
AI Security Category
AI-assisted attack
Part of the AI-Assisted Attacks topic.
Relevant Frameworks
RealGround Analysis
One message launched an autonomous campaign. RealGround analysis: internet-facing systems with known public exploits will be found and hit quickly.
Recommended Controls
- Patch internet-facing systems with public exploits first
- Reduce external attack surface
Related RealGround Service
AI Agent Business Logic Audit · or start with the free AI Agent Security Scanner.
Sources
thehackernews.com: https://thehackernews.com/2026/07/chinese-hacker-commands-deepseek-via.html
Summary and analysis written by RealGround from the source above; last updated 2026-10-18.