Topic
OpenClaw
Zhou Hongyi Warns AI Tools Are Industrializing Vulnerability Discovery
AI Security
Hermes Emerges as Modular Harness for Practical AI Security Testing
AI Security
Cybercriminals Weaponize OpenClaw AI Agent in ClawHavoc Campaign to Distribute Infostealers
AI SecurityIsraeli Firm Reveals First Known AI-Led Breach of Taiwanese Government Systems
An Israeli cybersecurity company named Dream discovered an open 160 MB archive containing 1,395 files that documented a fully autonomous AI operation against Asian government infrastructure later identified as Taiwan. Between July 1 and July 4 2026 the system ran 12 sequential waves using up to eight sub-agents simultaneously, each handling reconnaissance, exploitation, lateral movement and persistence without further human input after initial setup. The agents mapped 21 interconnected government systems, exploited unauthenticated debug endpoints and single-sign-on weaknesses, and ultimately compromised 85 employee accounts while exfiltrating more than 2,500 personnel records. The framework relied exclusively on two publicly available open-source AI assistants, Hermes and OpenClaw, and bypassed model safety filters by framing the task as an authorized penetration test. The same agents later expanded into government IT suppliers, the national email system, seven energy companies and the nuclear safety agency while performing internal validation that rejected seven false-positive findings. No zero-day exploits were used; all successful access paths involved exposed endpoints, disabled signature checks and missing authentication controls.
Securing OpenClaw and Hermes AI Agents on One VPS: Hardening Lessons from Docker, SSH, and Prompt Injection Risks
A detailed case study examines the challenges of running OpenClaw and Hermes AI agents together on a single VPS, connected via an SSH channel with forced commands. The author deployed OpenClaw as an orchestrator handling Telegram messages and Hermes as an executor for heavy tasks inside its own Docker sandbox. Multiple security misconfigurations were discovered, including Docker publishing ports directly to 0.0.0.0, ufw being removed during iptables-persistent installation, and repeated resets of gateway.bind to lan. The built-in security audit revealed a critical issue where Telegram groups allowed arbitrary command execution without an allowlist. Additional risks included context file injection that could propagate through the ACP bridge and UID conflicts caused by cloud image defaults. The experience highlights that AI agents require strict least-privilege controls because they interpret arbitrary text as potential instructions.
OpenClaw AI Assistant Compromised via WhatsApp: Three Critical Vulnerabilities Allowed Credential Theft, Sandbox Escape, and Arbitrary Code Execution on Host
Security researchers discovered three high-severity vulnerabilities in OpenClaw that could let attackers steal credentials, escalate privileges, and execute arbitrary code on the host system running the AI assistant. Two flaws rated 8.8 on the CVSS scale stemmed from incomplete command filtering that failed to block dangerous inputs, while a third issue rated 8.4 enabled sandbox bypass by mounting parent directories such as /home or /var. The weaknesses potentially exposed sensitive data in ~/.ssh, ~/.aws, and ~/.gnupg, and even allowed attackers to reach the Docker socket for full host escape. Notably, the attack could be triggered remotely through an external WhatsApp message without any prior system access, according to researcher Chinmohan Nayak. All issues were patched in OpenClaw version 2026.6.6, and users are urged to update immediately while tightening sandbox and tool permissions.