ClawHub
Back to skill

Security audit

安全审核标准_自动化

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed local scanner for other skill files, but its simple risk scores should not be treated as complete security approval.

Use this only as a first-pass local scanner. Invoke it intentionally, review or delete the generated JSON report if local paths are sensitive, and manually inspect any skill before installing instead of relying on a green score alone.

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
93% confidence
Finding
The trigger phrases are broad and generic enough to match normal user requests such as '安全审计' or '自动化', which can cause this skill to activate unintentionally. In a security-related skill, accidental activation is risky because it may initiate directory scanning or produce security judgments without explicit user intent, increasing the chance of misuse or confusion.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.