Back to skill

Security audit

OpenClaw Paid Actions

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed paid-action workflow that depends on a trusted external plugin and reviewed local scripts, with no bundled executable code in the artifact.

Install only if you trust the separate plugin implementation and have reviewed every configured action script. Protect the invoice secret and invoice store, verify the USDC recipient address, keep reviewed-script enforcement enabled, and require human approval for actions that post publicly or modify important accounts.

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.