ClawHub
Back to skill

Security audit

external-tech-acquisition

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed patent and technology-transfer research workflow with no executable code, persistence, or hidden data handling.

Installers should understand that this skill may send technology topics, patent numbers, organization names, and optional internal templates through configured PatSnap MCP tools and related skills. Use it only where that external research workflow and account authorization are acceptable, and avoid supplying confidential internal materials unless approved.

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
88% confidence
Finding
The trigger conditions are broad, relying on generic terms like external technology acquisition, technology introduction, and patent intelligence without explicit exclusions or stronger intent checks. This can cause the skill to activate in unintended contexts, leading the agent to initiate multi-step research, call dependent skills/tools, or steer users into a specialized workflow when they only asked a general question.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.