内容策略诊断

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Chinese content-strategy diagnosis template with no hidden execution, credential access, or privileged behavior.

Install this if you want content-strategy diagnosis primarily for Chinese creator workflows. Expect Chinese output by default, but the skill text allows users to request otherwise; there is no evidence of hidden code execution or sensitive data access.

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
95% confidence
Finding
The template is entirely written in Chinese and implicitly requires Chinese-language output without indicating whether this is a hard product constraint or a default that can be adapted to user preference. This can cause language-locking behavior, reducing usability, accessibility, and potentially causing the agent to ignore user locale needs or misunderstand multilingual requests.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal