Back to skill

Security audit

卖家之家(跨境电商)货盘搜索与发布

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed MJZJ marketplace helper that searches listings, uploads user-provided images, submits listing applications, and reads the user's own account data through MJZJ APIs.

Install this only if you intend to use MJZJ marketplace APIs and are comfortable providing MJZJ_API_KEY. Review listing details and image files before asking the agent to submit a publish application, and treat returned account/listing data as sensitive business information.

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
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 (8)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The file's operational description, trigger guidance, error messaging, and usage examples are entirely Chinese-language, which effectively forces a specific language for use of the skill. The policy allows locale constraints only when the skill offers user opt-in or clearly documents a justified region/language limitation, which is not stated here.

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 155)May include surrounding context.

1) 获取货盘标签分组(公开)

bash
curl -X GET "https://data.mjzj.com/api/pallet/groupLabels" \
  -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 155)May include surrounding context.

1) 获取货盘标签分组(公开)

bash
curl -X GET "https://data.mjzj.com/api/pallet/groupLabels" \
  -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 162)May include surrounding context.

1) 获取货盘标签分组(公开)

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

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

This flow sends an Authorization bearer token to an external service and obtains a temporary upload URL for direct file transfer. While expected for the feature, it increases security sensitivity because a compromised or misconfigured skill could expose API keys or cause user-provided files and metadata to be uploaded to unintended storage if the returned putUrl/path are not tightly validated.

Content

Scanner excerpt · SKILL.md (reported line 169)May include surrounding context.

3) 申请上传临时文件(封面或介绍图)

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
87% confidence
Finding

This endpoint performs an authenticated external submission that can publish marketplace content on behalf of the user account. In context, this is intended functionality, but it is security-relevant because misuse could create unauthorized listings, leak business data, or abuse the user's account if invocation lacks strong user confirmation and strict parameter validation.

Content

Scanner excerpt · SKILL.md (reported line 190)May include surrounding context.

4) 申请发布货盘(需审核)

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

External Transmission

Medium
Category
Data Exfiltration
Confidence
85% confidence
Finding

This authenticated external request retrieves the user's private marketplace inventory data. Even though it matches the skill purpose, it handles account-specific information, so insufficient consent boundaries or weak secret handling could expose sensitive business records to unauthorized parties or logs.

Content

Scanner excerpt · SKILL.md (reported line 213)May include surrounding context.

5) 查询我的货盘(需鉴权)

bash
curl -X GET "https://data.mjzj.com/api/palletManage/getPallets?onSale=true" \
  -H "Authorization: Bearer $MJZJ_API_KEY" \
  -H "Content-Type: application/json"

External Transmission

Medium
Category
Data Exfiltration
Confidence
85% confidence
Finding

This endpoint accesses the user's private application/review status data using a bearer token. The operation is legitimate for the skill, but any authenticated retrieval of private account data is dangerous if the token is mishandled, the response is overshared, or the action can be triggered without clear user authorization.

Content

Scanner excerpt · SKILL.md (reported line 221)May include surrounding context.

6) 查询我的申请(需鉴权)

bash
curl -X GET "https://data.mjzj.com/api/palletManage/getApplications" \
  -H "Authorization: Bearer $MJZJ_API_KEY" \
  -H "Content-Type: application/json"

Static analysis

No suspicious patterns detected.