ClawHub
Back to skill

Security audit

search-patents-ip

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed patent-search workflow that creates local search artifacts and uses patent MCP connectors for its stated purpose.

Before installing, confirm you are comfortable sending patent-search scope, terms, and identifiers to the configured PatSnap MCP services, especially if the project includes confidential terminology. The skill appears proportionate and transparent for patent-search preparation.

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
Findings (1)

Natural-Language Policy Violations

Low
Confidence
91% confidence
Finding
Line L248 instructs users to "Use stable, internationally clear English terms," which imposes a specific language choice in the skill guidance. The file does not present this as optional, nor does it offer user opt-in or a justified region-specific constraint.

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.