ClawHub
Back to skill

Security audit

立创商城自动化技能

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent LCSC/JLC browser-automation helper, but it enables purchases, order access, and design-file uploads without clear confirmation safeguards.

Install only if you want an agent to automate LCSC/JLC storefront work. Before letting it add items to carts, upload BOM/PCB files, view order data, or place orders, require a fresh explicit confirmation that includes destination site, files, quantities, price, shipping, and manufacturing parameters. Avoid using cookie import/export or JavaScript evaluation unless you specifically asked for it.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly supports shopping-cart management, order placement, order-status access, and other account-affecting actions, but it does not require confirmation gates, warn about purchases, or distinguish read-only from transactional operations. In an agentic context, this can lead to unintended purchases, disclosure of order history or logistics data, and irreversible user-account actions if the agent follows broad user prompts automatically.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The example workflows normalize BOM uploads and PCB/SMT ordering without any safety language around file sensitivity, manufacturing cost, or irreversible submission. Because these examples are prescriptive, an automation agent may treat uploads and order-placement as routine steps, increasing the chance of accidental disclosure of proprietary design files or unintended manufacturing orders.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The description is written to enforce use for a Chinese storefront workflow and is phrased entirely in Chinese without any mention of allowing the user to choose language or locale. Under SQP-3, forcing a specific language or locale without opt-in can be a policy violation unless the locale constraint is documented and justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.