ClawHub
Back to skill

Security audit

skill-advisor

Security checks across malware telemetry and agentic risk

Overview

This is a text-only skill that helps review other OpenClaw skills before installation, with no evidence of hidden execution, persistence, credential access, or destructive behavior.

Reasonable to install if you want help evaluating skills before installation. Treat reviewed SKILL.md content as untrusted, and use the advisor's score as guidance rather than a substitute for checking sensitive permissions yourself; the broad trigger wording may make it appear in general install-advice conversations.

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 (1)

Vague Triggers

Medium
Confidence
85% confidence
Finding
The trigger set includes broad natural-language phrases such as "帮我看看这个skill怎么样" and "Should I install {skill-name}?", which can overlap with ordinary conversation and cause the skill to activate unexpectedly. Because this skill is designed to assess safety and installation decisions, over-triggering could lead to unintended tool use, confusing responses, or interception of requests meant for other skills.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.