乔布斯视角

Security checks across malware telemetry and agentic risk

Overview

This is a Chinese-language advisory skill that provides a Steve Jobs-style product and strategy perspective without code execution or sensitive access.

Install this if you want an opinionated Chinese-language product and strategy advisor. Specify another language when needed, and treat the persona-based output as a perspective rather than factual authority or a substitute for current fact-checking.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 sets Chinese as the default output language unless the user says otherwise. This can override user or system expectations and cause unintended language switching, reducing usability and potentially obscuring important safety, compliance, or operational guidance for users who expect another language. In this context it is not inherently malicious, but it is still a real policy/quality vulnerability because it changes output behavior without explicit user opt-in.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal