OpenClaw Security Scanner

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed local OpenClaw security scanner that reads local security-related files and only changes files when the user explicitly runs and confirms auto-fixes.

Run the default scan first. Use --fix only when you understand each displayed command, and review any --report output before sharing because it can reveal local paths and security findings about your OpenClaw setup.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill advertises and invokes shell execution via bash, but no corresponding permissions are declared in the skill metadata. This creates a trust and enforcement gap: users or hosting systems may treat the skill as low-privilege while it actually performs local code execution, including a write-capable '--fix' mode that can modify system and application files.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal