Cases › security breach › LR-2026-0679
China-based operator used DeepSeek through Hermes Agent in attempted cyberattacks on 460 systems
Preliminary Why: 1 report: Startup Fortune · subject to change · 1 independent report
Status: no action reported
No source states: loss or records, developer and model, deployer, industry.
Severity moderate: test: data of others touched (exfiltration from three NetScaler targets) with a bounded scope stated (three targets, eleven endpoints, nine servers, three VPN endpoints).
A China-based operator used DeepSeek through the open-source Hermes Agent framework to automate parts of hacking, including finding targets, pulling exploit code and deciding when to move on. Hermes gave the model terminal commands, internet searches, exploit downloads and local files, and the operator controlled the setup through Telegram. Unit 42 recovered a session from May 7 in which DeepSeek probed exposed Langflow and n8n systems found through FOFA. Those n8n attempts did not produce a breach. The confirmed damage came from separate manual operations. Later, Hermes started a Python HTTP file server from the operator's home directory, which exposed model configurations, API keys, exploit scripts, target lists, bash history and session logs. Unit 42 reported that the actor attempted to exploit more than 460 targets through a mix of autonomous and manual techniques.
What happened
What was done
No source states an action or fix.
Risks
Primary96 incidents
Rising: 24 vs 4.0 a week
Read from the sources; not yet reviewed by a person.
Controls
Not yet read for controls. Controls that mitigate the primary risk:
ModelSafety training and refusal · Cyber and weapons safeguards · Abuse monitoring and account enforcement · Staged or restricted release · Dangerous-capability testing before release · Outside red-teaming · Content safety classifiers · Safeguards kept on in testing · Reasoning monitoring
Infrastructure / targetKnown flaws patched · Multi-factor sign-in and password policy · Network segmentation · Intrusion and endpoint detection · Backups and recovery · Phishing and fraud filters
Similar incidents
Evidence
No source states: what went wrong, what it reached or did, how it was caught, when it happened, when it was found, how many records were exposed, the direct loss, a count of the other parties affected, any court case, the cause, what set it off, what was done.
Show the full account: 2 items from the primary sources
What happened, in order
- May 7 Hermes Agent session in which DeepSeek worked through exposed Langflow and n8n systems.
- July 30 Unit 42 report published, describing the operator controlling the setup through Telegram.
Show every field, with its source and grade
The AI system
What happened
Impact
Context
Notes on gaps
Years for the May 7 session and July 30 report are not stated, so no full dates were written. The 460 figure is targets attempted, not systems compromised. No remediation was reported.
LR-2026-0679 · version 1 · published 2026-11-01 after automatic checks; not yet checked field by field by a person · JSON