全球选品雷达

• Outcome: Pass
• Latest audit: Jun 10, 2026 at 8:21 AM UTC
• Version:
  1.0.0

Overview

This is a product-research skill for e-commerce analysis, with no artifact-backed evidence of hidden execution, credential use, persistence, or destructive behavior.

Install only if you want an assistant to perform e-commerce product and supplier research across public marketplaces and related data sources. Expect Chinese-oriented output and verify any market, profit, or supplier claims before making business decisions.

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: 87% confidence
• Finding: The skill defines broad capabilities across many platforms and workflows but does not constrain when it should activate or what user intents it is allowed to handle. This can cause over-broad invocation, unexpected data gathering or analysis behaviors, and increase the chance the agent applies the skill in inappropriate contexts.

Natural-Language Policy Violations

Medium

• Confidence: 94% confidence
• Finding: The skill content is written as a directive that the assistant is a Chinese-language product analysis system, with no indication that language should follow user preference. Forcing a language without opt-in can degrade usability, cause misunderstanding of risk disclosures, and interfere with safe operation when the user expects another language.

VirusTotal

64/64 vendors flagged this skill as clean.