alphashop-sel-newproduct

• Outcome: Review
• Latest audit: May 28, 2026 · 12:10 PM UTC
• Version: 1.0.0

Overview

This skill appears to do the AlphaShop product-research work it describes, but it needs review because required API credentials and outbound API use are under-declared and documented inconsistently.

Install only if you trust AlphaShop with your product-research queries and use a dedicated, revocable API key. Prefer OpenClaw secret/env management over plaintext .env files, do not commit credential files, avoid running test.sh with an untrusted .env, and review saved JSON reports for sensitive business data.

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (8)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 83% confidence
• Finding: The skill declares `primaryEnv: none` and no required environment permissions, yet the documentation clearly indicates use of environment-held API credentials, network access to external endpoints, and file output under `output/`. This mismatch is dangerous because it hides the skill's real capabilities from reviewers and operators, undermining least-privilege controls and informed consent about external data transmission and local artifact creation.

Intent-Code Divergence

Medium

• Confidence: 95% confidence
• Finding: The document first instructs users to configure `ALPHASHOP_ACCESS_KEY` and `ALPHASHOP_SECRET_KEY`, then later states `无需鉴权` and that the API is public and needs no token. This contradiction is security-relevant because it can lead operators to mis-handle secrets, send credentials unnecessarily, or misunderstand whether the remote service is authenticated, all of which increase the risk of credential exposure and unsafe deployment assumptions.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The quickstart instructs users to place long-lived API credentials directly in shell commands, a .env file, and a plaintext OpenClaw config without any warning about shell history, file permissions, accidental commits, or secret rotation. This creates a real risk of credential leakage through terminal history, local filesystem exposure, backups, screenshots, or source control, especially because these keys appear to grant access to a commercial platform API.

Missing User Warnings

Medium

• Confidence: 98% confidence
• Finding: Using 'source .env' executes the contents of the local .env file in the current shell rather than merely parsing key-value pairs. If the .env file is modified by an attacker or contains shell metacharacters/commands, running the test script can trigger arbitrary code execution and expose any credentials loaded into the shell.

External Transmission

Medium

• Category: Data Exfiltration

Content

| 接口 | 方法 | URL | 响应耗时 |
|------|------|-----|---------|
| 关键词搜索API | POST | `https://api.alphashop.cn/opp.selection.keyword.search/1.0` | 10秒内 |
| 新品报告API | POST | `https://api.alphashop.cn/opp.selection.newproduct.report/1.0` | 10秒内 |

## 注意事项

• Confidence: 79% confidence
• Finding: The skill documents POST requests to an external domain, meaning user-provided keywords, filters, and possibly derived market-selection data will be transmitted off-platform. In this skill's context, external transmission is expected for its core functionality, but it is still security-relevant because the manifest does not clearly disclose network permissions and the documentation is inconsistent about authentication, which makes the transmission less transparent and more risky.

External Transmission

Medium

• Category: Data Exfiltration

Content

| 接口 | 方法 | URL | 响应耗时 |
|------|------|-----|---------|
| 关键词搜索API | POST | `https://api.alphashop.cn/opp.selection.keyword.search/1.0` | 10秒内 |
| 新品报告API | POST | `https://api.alphashop.cn/opp.selection.newproduct.report/1.0` | 10秒内 |

## 注意事项

• Confidence: 79% confidence
• Finding: This is a second documented external API endpoint on the same third-party domain for generating reports, which also implies outbound transmission of user inputs and possibly business-sensitive selection criteria. The risk is amplified by the skill context because it writes reports locally and relies on remote processing, yet the permission model and auth story are not presented consistently, reducing operator visibility into data handling.

Credential Access

High

• Category: Privilege Escalation

Content

# 复制示例文件
cp .env.example .env

# 编辑 .env 文件，填入真实凭证
vim .env

# 加载环境变量

• Confidence: 90% confidence
• Finding: The guide explicitly instructs users to create a .env file containing real API secrets. While .env usage is common, presenting it without any controls or warnings encourages storage of live credentials in plaintext, which can be stolen via accidental repository commits, local compromise, CI artifact leakage, or insecure file sharing.

Credential Access

High

• Category: Privilege Escalation

Content

cp .env.example .env

# 编辑 .env 文件，填入真实凭证
vim .env

# 加载环境变量
source .env

• Confidence: 88% confidence
• Finding: The instruction to edit a .env file and populate it with real credentials reinforces a plaintext secret-storage workflow without any compensating safeguards. In the context of an API-driven e-commerce analysis skill, compromise of these credentials could enable unauthorized API usage, data access, quota abuse, and account-level financial or operational impact.

Static analysis

No suspicious patterns detected.