Chinese Public Opinion & Sentiment Analysis Report Writer

Security checks across malware telemetry and agentic risk

Overview

This is a Chinese-language report-writing skill for public-opinion analysis, with no code execution, install scripts, credential access, persistence, or hidden data handling.

Install this only if you want Chinese public-opinion analysis report drafting. Because the topic can involve sensitive government, enterprise, or political analysis, verify all web-sourced facts, avoid unsupported claims, and ask for bilingual or non-Chinese output when reviewers need to audit the result.

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
88% confidence
Finding
The skill explicitly requires Chinese-only output regardless of user preference, which can override the user's requested language and reduce transparency or informed review by non-Chinese-speaking operators. In a government/public-opinion reporting context, this can also increase the chance that downstream reviewers miss problematic content, policy-sensitive framing, or unsafe recommendations because the output locale is forcibly constrained.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal