ClawHub
Back to skill

Security audit

卖家之家(跨境电商)服务产品搜索与发布

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed marketplace-search and product-submission helper that uses the expected vendor APIs and API key for its stated purpose.

Install this only if you intend to connect an MJZJ seller account and allow the agent to search products, upload product images, and submit new product applications for review. Before using publish or upload flows, verify the API key belongs to the intended account and review the product details and files before submission.

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 (6)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill description and all operational instructions are written as Chinese-only directives for product search and publishing, and the prompt supplement instructs routing to this skill based on user intent without any opt-in for language preference. This can violate language/locale policy because the skill appears to assume a fixed language rather than offering the user a choice.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 129)May include surrounding context.

1) 获取服务商产品标签分组（公开）

bash
curl -X GET "https://data.mjzj.com/api/spQuery/getProductLabelGroups" \
  -H "Content-Type: application/json"

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 129)May include surrounding context.

1) 获取服务商产品标签分组（公开）

bash
curl -X GET "https://data.mjzj.com/api/spQuery/getProductLabelGroups" \
  -H "Content-Type: application/json"

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 136)May include surrounding context.

1) 获取服务商产品标签分组（公开）

bash
curl -X GET "https://data.mjzj.com/api/spQuery/getProductLabelGroups" \
  -H "Content-Type: application/json"

External Transmission

Medium
Category
Data Exfiltration
Confidence
84% confidence
Finding

This endpoint sends authenticated metadata for file uploads using the bearer API key and initiates transfer of user-provided files to an external storage service via returned putUrl values. While this is part of intended functionality, it creates real data-exposure risk because sensitive images and authorization context are transmitted off-platform, and an agent following arbitrary putUrl responses without strict validation could upload data to an untrusted destination.

Content

Scanner excerpt · SKILL.md (reported line 143)May include surrounding context.

3) 申请上传临时文件（封面或详情图）

bash
curl -X POST "https://data.mjzj.com/api/common/applyUploadTempFile" \
  -H "Authorization: Bearer $MJZJ_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

External Transmission

Medium
Category
Data Exfiltration
Confidence
80% confidence
Finding

This authenticated product-submission call transmits user-supplied business content, file references, and marketplace metadata to an external service. In context it is intended, but it is still a genuine security-relevant sink because it can publish or leak sensitive commercial information externally, especially if the agent submits data without strong user confirmation or if malicious prompt content tricks the agent into posting unintended material.

Content

Scanner excerpt · SKILL.md (reported line 164)May include surrounding context.

4) 新建产品申请（需审核）

bash
curl -X POST "https://data.mjzj.com/api/spProduct/applyNewProduct" \
  -H "Authorization: Bearer $MJZJ_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

Static analysis

No suspicious patterns detected.