Yunlv Product Desc

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:44 PM UTC
• Version:
  1.1.0

Overview

This is a coherent product-description skill that discloses its TradeGPT API use and local output storage, with some routing and data-handling caveats users should understand.

Install only if you are comfortable sending product specs, draft listings, pricing claims, and optional competitor comparisons to Yunlv/TradeGPT. Use a revocable API key, avoid unreleased or confidential commercial data unless the provider terms are acceptable, and be aware the skill may match broad SEO/product-description requests.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Intent-Code Divergence

Medium

• Confidence: 96% confidence
• Finding: The file claims generated content is "not stored," yet it also defines local storage paths and explicitly permits writing generated descriptions to disk. This creates a misleading privacy representation that can cause users to submit sensitive product, pricing, or competitor information under false assumptions, increasing confidentiality and compliance risk.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: Broad triggers like "SEO" and "差异化" can activate the skill in unrelated conversations, causing unintended routing of user input into this workflow. In this skill, accidental activation matters because the workflow may transmit supplied product and competitor data to an external API and write outputs locally, creating avoidable privacy exposure and unexpected processing.

Missing User Warnings

Medium

• Confidence: 98% confidence
• Finding: The skill permits sending user-supplied product and competitor information to a third-party API and storing generated content locally, but it does not clearly warn users of those data flows. This is dangerous because business-sensitive data such as unreleased specifications, pricing, supplier details, and competitor analysis may be disclosed externally or retained on disk without informed user consent.

Vague Triggers

Medium

• Confidence: 84% confidence
• Finding: The manifest description contains broad usage language such as general product-description, localization, SEO, and listing creation requests that can cause the skill to activate on a wide range of ordinary writing tasks. Over-broad activation increases the chance of unintended routing to an external API, which may expose user business data or produce actions the user did not specifically request.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The trigger list includes generic phrases like "SEO", "产品描述", and "product description", which are ambiguous and likely to match many benign user requests outside the intended narrow skill scope. If auto-invoked, the skill may unnecessarily send sensitive draft product, catalog, or commercial information to the third-party TradeGPT API without sufficiently specific user intent.

VirusTotal

65/65 vendors flagged this skill as clean.