ClawHub
Back to skill

Security audit

patent-portfolio-report

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Chinese patent-portfolio reporting workflow that uses Patsnap MCP searches and generates report files without hidden persistence or destructive behavior.

Install this only if you intend to use Patsnap MCP with authorized patent-data access and are comfortable producing Chinese-language report deliverables. Review any generated patent, customer, competitor, and stakeholder information before sharing it externally.

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

Medium
Confidence
91% confidence
Finding
The skill explicitly requires Chinese-only output for all report generation, but the metadata and content do not state that the skill is restricted to Chinese-speaking users or that user language preference will be honored. This can override a user's requested language, reduce usability and accessibility, and create policy/compliance issues in multilingual environments where accurate review by stakeholders depends on output in the user's chosen language.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.