Back to skill

Security audit

pps-tag

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed patent-taxonomy workflow that reads user-provided patent files, optionally uses PatSnap MCP tools, and writes scoped output files without hidden persistence or destructive behavior.

Install only if you intend to use PatSnap MCP services for patent analysis and are comfortable sending relevant patent/project data to that configured service. Keep API keys in the MCP/client configuration rather than project files, and review generated exports before sharing them with a customer SaaS tool.

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

42/42 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.