Install Hirey AI on OpenClaw

Security checks across malware telemetry and agentic risk

Overview

This skill makes real local OpenClaw installation and routing changes for Hirey AI, but the behavior is disclosed, scoped to that install purpose, and uses user-local paths.

Install this only if you want this OpenClaw host connected to Hirey AI/Hi. Expect it to install local npm packages, enable OpenClaw hook ingress, write MCP configuration, generate/store a hook token, bind the current chat for replies, and register with the external Hi service. Review the --force reinstall and cleanup behavior if you have customized an existing Hirey AI/OpenClaw setup.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The setup path performs state-changing actions immediately: it installs npm packages, writes persistent OpenClaw hooks and MCP configuration, and creates a manifest, but the script itself does not require an interactive confirmation or an explicit acknowledgement flag before those mutations occur. In an agent-skill context, this is risky because a caller may trigger durable host changes through natural-language automation, causing unintended local system modification and service integration without clear runtime consent.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The cleanup path removes the persisted manifest and unsets host hooks/MCP configuration without any execution-time confirmation, so invoking cleanup can silently disable or partially remove an installed integration. In an agentic environment this creates a meaningful integrity/availability risk, because an automated or mistaken call can alter host state and break service routing or registration with no final safeguard.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal