ClawHub
Back to skill

Security audit

检验指导书（SIP）生成技能

Security checks across malware telemetry and agentic risk

Overview

This skill appears to generate inspection-guide spreadsheets from user-provided technical files without hidden network, credential, persistence, or destructive behavior.

Before using this skill, review technical documents and templates for confidential product, supplier, pricing, or quality data and redact anything unnecessary. Generated spreadsheets are saved locally, so use an appropriate working directory and check any entries marked as needing confirmation.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (1)

Missing User Warnings

Medium
Confidence
86% confidence
Finding
The skill instructs users to upload product technical files, templates, test reports, and supplier-related quality requirements, all of which commonly contain sensitive commercial, engineering, or supplier data, yet it provides no warning or handling guidance. In this context, omission of a sensitivity warning increases the risk of inadvertent disclosure, over-sharing, or improper processing of confidential documents through the agent workflow.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.