ClawHub
Back to skill

Security audit

证据化通用标引

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent labeling workflow that uses disclosed PatSnap/Zhihuiya MCP evidence tools and local validation helpers without hidden or destructive behavior.

Install only if you intend to use PatSnap/Zhihuiya MCP services for evidence-backed labeling. Do not provide sensitive datasets unless you are comfortable with selective MCP enrichment calls, and keep API keys in the MCP/client configuration rather than chat.

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

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.