Accomplish and excel in any task

Security checks across malware telemetry and agentic risk

Overview

This is a low-capability workflow-template skill whose broad “any task” wording is worth noticing but does not create hidden access or unsafe behavior by itself.

Install only if you want a general Chinese-language workflow/process aid. Because it is framed for almost any task, use clear instructions when you want a more specific skill or domain-specific guidance instead.

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

High
Confidence
96% confidence
Finding
The description says the skill applies when doing 'anything', creating an activation scope broad enough to match nearly any user request. That can cause the agent to invoke this generic process skill in inappropriate contexts, overriding more specific safeguards or workflows and leading to unsafe, irrelevant, or policy-conflicting behavior.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal