shiny-teaching-dashboard

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This skill provides Chinese-language guidance and templates for creating R Shiny teaching dashboards, with no evidence of hidden data access, persistence, or destructive behavior.

Install this if you want help creating R Shiny teaching dashboards, especially in Chinese. Review generated app.R files before running them, and install suggested R packages only from trusted CRAN sources when needed.

SkillSpector (2)

By NVIDIA

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The trigger conditions are explicitly broad and auto-activate on vague phrases like '用 Shiny 做个教学演示' or '不想用 PPT 了', which can cause the agent to invoke this skill when the user has not clearly requested this specific workflow. That creates scope hijacking risk: the skill may steer responses toward generating Shiny artifacts and file-writing behavior even when a simpler or different solution would be more appropriate.

Natural-Language Policy Violations

Medium

Confidence: 88% confidence
Finding: The skill metadata and content are written to assume Chinese-language interaction and do not provide a user-language fallback or instruction to preserve the user's language. This can cause unauthorized language switching, reducing transparency and increasing the chance the user cannot effectively review generated code, commands, or safety-relevant instructions.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal