Shell command execution detected (child_process).
Critical
- Code
- suspicious.dangerous_exec
- Location
- index.ts:82
- Evidence
return execFileSync(bin, args, {
Security audit
Composio Agent Orchestrator
Security checks for vulnerabilities and agentic risk
Overview
This looks like a legitimate Agent Orchestrator integration, but it gives OpenClaw broad command-execution and background-agent control that should be reviewed before use.
Use this only if you want OpenClaw to control Agent Orchestrator from a specific project directory. Configure trusted ao and gh binary paths, limit GitHub privileges, review the AO project configuration, and disable background polling if you do not want ongoing automated activity.
Static analysis
Detected: suspicious.dangerous_exec