Chinese Hacker Commands DeepSeek via Telegram to Launch Autonomous Attacks
- ID
- 9619
- Status
- summarized
- Published
- 31 Jul 2026, 7:21 PM
- Fetched
- 31 Jul 2026, 9:51 PM
- Provider
- The Hacker News
- Category
- security
- Original URL
- https://thehackernews.com/2026/07/chinese-hacker-commands-deepseek-via.html
- Source URL
- https://feeds.feedburner.com/TheHackersNews
Summary
- Score
- 7.5
- Created
- 31 Jul 2026, 9:51 PM
- Tags
- Audience
- developersai_agent_usersai_ml_learners
What happened
Palo Alto Networks' Unit 42 reports a Chinese-speaking threat actor used DeepSeek via the open-source Hermes Agent framework to autonomously attack 460+ targets after a single Telegram instruction, with no further operator input. The agent selected CVEs, downloaded exploits, and abandoned unproductive paths on its own, but only 3 targets were confirmed successfully exploited. The operation was exposed because Hermes Agent inadvertently started an HTTP server leaking API keys, exploit scripts, target lists, and session logs.
Why it matters
If you run exposed Langflow, n8n, Marimo, or customer-managed NetScaler ADC/Gateway as a SAML IdP, patch now and remove unnecessary public access to workflow and notebook interfaces—these are the exact CVEs targeted. For AI agent builders, this is a concrete example of how autonomous agent frameworks can leak secrets (API keys, target lists, shell history) when terminal access and unattended execution are combined without sandboxing.
Discussion angle
The agent's autonomous decision-making (checking versions, ranking CVEs by severity and exploitability, abandoning dead ends) is impressive but the real lesson is operational security: the framework leaked everything via an accidental HTTP server. How should agent frameworks isolate secrets and prevent self-exposure when given terminal access?