Chinese Daily Assistant

• Outcome: Pass
• Latest audit: May 28, 2026, 10:34 AM
• Version:
  1.0.1

Overview

This is a simple local Chinese daily-assistant skill with broad triggers but no evidence of hidden data access, persistence, network calls, or destructive behavior.

Safe to install from a security perspective based on the artifacts reviewed. Treat the weather, exchange-rate, and festival countdown outputs as static demo data rather than live facts, and be aware that generic trigger words may make this skill answer ordinary weather or translation requests.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

• Confidence: 84% confidence
• Finding: The trigger phrases include very broad everyday expressions such as asking about today's weather or health advice, which can cause the skill to activate unintentionally during ordinary conversation. In an agent environment, over-broad activation can route user input to the wrong skill, causing confusing behavior, privacy leakage of nearby context, or unintended execution of skill capabilities.

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The trigger list includes very generic terms such as "weather," "translate," "tip," and their Chinese equivalents, which can cause the skill to activate in many ordinary conversations unrelated to this package. This increases the chance of unintended invocation, context hijacking, or user confusion, especially in ecosystems where trigger matching is broad or ambiguous.

VirusTotal

64/64 vendors flagged this skill as clean.