ClawHub
Back to skill

Security audit

电商主图详情页诊断

Security checks across malware telemetry and agentic risk

Overview

This appears to be a product-listing analysis skill with some broad triggers and automatic link fetching, but no evidence of credential access, persistence, destructive behavior, or deception.

Install if you want an e-commerce product-image/detail-page analysis helper. Before using it on links, assume the agent may fetch those pages; avoid giving private, internal, or sensitive URLs, and review generated recommendations before acting on them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger conditions are very broad and overlap with ordinary conversation, such as generic mentions of 'analysis' or asking whether a main image is good. Over-broad activation can cause the skill to run unintentionally, increasing the chance of unnecessary file generation, unintended processing of user content, or confusing workflow hijacks in unrelated chats.

Vague Triggers

Medium
Confidence
82% confidence
Finding
The description embeds a long list of colloquial trigger phrases without guardrails, including everyday requests like '帮我看看主图' and '分析详情页'. This broad phrasing makes accidental routing more likely and can cause unintended collection or processing paths, especially in systems that auto-select skills from descriptions.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill states that product links may be automatically fetched for product name, platform, and image URLs, but it does not warn the user that network access and external data retrieval may occur. This is dangerous because users may disclose links expecting passive analysis, while the skill could perform outbound requests, creating privacy, consent, and SSRF-style risk depending on the execution environment.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.