patent-expert

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward patent-assistance skill with a few clarity cautions but no evidence of hidden, destructive, or data-stealing behavior.

Install if you want a Chinese patent-workflow assistant. Avoid sharing proprietary invention details unless you are comfortable putting them into the agent context, verify legal conclusions with a qualified patent professional, and review any generated Python/Graphviz script before running it locally.

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 description matches a very broad set of common patent-related terms, which can cause the skill to activate outside its intended scope and intercept generic user requests. In an agent system, over-broad routing can mis-handle user intent, expose unrelated context to a specialized skill, and increase the chance of unsafe or low-quality downstream actions.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal