ClawHub
Back to skill

Security audit

Skill Vetting

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a purpose-aligned security vetting tool, with scanner-like file, command, and network guidance that is expected for its stated role.

Install this if you want an agent-assisted scanner for reviewing OpenClaw skills. Expect it to read local skill artifacts and run scanner logic; review any requested shell or network action before approving it, especially if pointed at private files or remote sources.

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
94% confidence
Finding
The skill instructs users to perform network access, shell execution, and local file reads, but it declares no permissions to reflect those capabilities. This creates a trust and transparency gap: reviewers or users may approve the skill under an incomplete security model, increasing the chance of unexpected data access or command execution during use.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dynamic_code_execution, suspicious.prompt_injection_instructions

Dynamic code execution detected.

Critical
Code
suspicious.dynamic_code_execution
Location
scripts/scan.py:22

Prompt-injection style instruction pattern detected.

Warn
Code
suspicious.prompt_injection_instructions
Location
references/patterns.md:108