Back to skill

Security audit

openclaw intent router

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed local intent-routing helper, with the main caution that its docs point users to an external npm/GitHub package not bundled in the reviewed artifact.

Reasonable to install as a routing helper, but verify the referenced npm package or GitHub repository before running it, prefer pinned versions, and require explicit user confirmation before any routed handler sends messages, modifies accounts/data, publishes content, spends money, or performs other irreversible actions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.