HiddenLayer
mitre-atlas-cs0051
OpenClaw Command & Control via Prompt Injection
- Autonomous Agents
- Tool Integrations & MCP
- Model Poisoning & Integrity
- Resource Hijacking & Cost
- System Compromise & RCE
A curated AI-agent incident flow showing indirect prompt injection, malicious tool invocation, persistent agent configuration poisoning, and command-and-control behavior.