AML.S0026 · Tool · ai-agent, ai-agent-framework
OpenClaw
OpenClaw is an open source AI assistant that runs on user-controlled infrastructure. Its gateway connects configurable language models to messaging channels, external tools, skills, and persistent workspace context. It supports tasks such as web browsing, file operations, and command execution through conversational interfaces.[[canonical-source]]
On ShieldMap: npm:openclaw
Case studies that used it
- Multi-Agent Framework Compromises Taiwanese Government SystemsIncident · 2026-07-01 to 2026-07-04
References
- Inside a Multi-Agent AI Framework Used to Compromise Government Entities in Asia
- Overseas hackers launch AI-agent attacks against government agencies; MODA activates coordinated response and strengthens cyber defenses
- China-linked hackers hit Taiwan in unprecedented 'autonomous' AI cyber attack
- Exploring the Security Risks of AI Assistants like OpenClaw
- OpenClaw: canonical implementation source
From MITRE ATLAS 2026.10 (Apache-2.0). Prompt packages listed in ATLAS are left out of ShieldMap.