ClawHub
Back to skill

Security audit

选品助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent e-commerce product research assistant, with disclosed web research and local HTML report generation, though users should avoid entering sensitive unreleased product details.

Install only if you are comfortable with product names, descriptions, ASINs, and related market-research terms being used in web searches. Avoid pasting confidential supplier data or unreleased product plans, and open generated HTML reports with normal caution because they load Chart.js from a CDN and include analysis text in the page.

SkillSpector

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)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill states that it will automatically search market data online, but the README provides no notice that user-supplied product descriptions, ASINs, or related inputs may be transmitted to external services. This creates a meaningful privacy and data-handling risk, especially in e-commerce settings where users may paste proprietary product ideas, supplier details, or unreleased listings.

Vague Triggers

Medium
Confidence
78% confidence
Finding
The trigger rules are broad enough to activate on ordinary product-related conversation, causing the skill to run in contexts where the user did not clearly request market analysis. Accidental activation increases the chance of unnecessary web/file actions, confusing outputs, and unintended reliance on a specialized workflow.

Vague Triggers

Medium
Confidence
76% confidence
Finding
Several trigger phrases are generic conversational language, so the skill may activate from benign discussion rather than a deliberate request to perform analysis and generate a report. In this skill's context, that broad activation is more concerning because activation can lead to searches, file writes, and authoritative-looking business recommendations.

Static analysis

No suspicious patterns detected.