Product
Hermes
- First Reported
- Jun 30, 2026
- Latest Reported
- Oct 6, 2026
Reported Context (5)
- business endpoints, about 0.018% are running one: roughly 1 in 5,600 machines. Two agents, Hermes and OpenClaw, account for nearly all the activity found; four of the eight tools tracked have never been Acronis Data Shows AI Agent Use Across MSP and SMB Endpoints
- Dream’s reconstruction says a Hermes and OpenClaw setup ran up to eight subagents in parallel, mapped 21 connected government systems, cracked 85 employee credentials, and extracted at least 2,564 personnel records in AI-Assisted Taiwan Campaign, OpenAI Testing Pause and Other Cybersecurity News
- AI attack fleet: The operator drives multiple AI coding agents (Claude Code, Codex, and the open-source Hermes and pi agents) in full-auto mode with every safety approval disabled, tasking and monitoring them CloudSEK Finds AI-Agent-Driven Campaign Behind 12,000 WordPress Backdoors and Crypto Theft
- An operator used the Hermes AI assistant in YOLO mode to autonomously probe Thailand’s Ministry of Finance network, including host scans, privilege-escalation checks, and directory crawls of internal personnel records. Hunt.io Reports Unattended Hermes AI Agent Used in Thai Finance Ministry Intrusion
- “We tested eleven popular open source agents, including Hermes, OpenCode, Roo-code, and others,” explains Omer Ben Simon, lead researcher at Adversa AI. GuardFall Bash Tricks Bypass Guards in Most Tested AI Coding Agents
CVE (7)
Malware (5)
People (4)
Threat Actors (1)
MITRE ATT&CK (13)
Vendors (20)
Products (46)
Tools (17)
Industries (7)
Countries (28)
Note: Related entities, including threat actors, malware, CVEs, MITRE ATT&CK techniques, vendors, products, tools, countries, and industries, are shown when they appear in the same reporting. Their presence does not necessarily mean they were targeted, compromised, vulnerable, responsible for the activity, or directly involved in the incident.
