ClawHub
Back to skill

Security audit

ReadGZH -- 微信公众号文章 AI 阅读器

Security checks for vulnerabilities and agentic risk

Overview

This skill clearly connects an agent to ReadGZH so it can retrieve public WeChat articles, with the main risk being disclosed shared cloud caching.

Install only if you are comfortable sending public WeChat article URLs to ReadGZH and having converted content potentially enter a shared cache. Do not use it for private, internal, sensitive, deleted, or access-restricted articles, and keep API keys in the client’s secure credential mechanism rather than in prompts or URLs.

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 (4)

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 31)May include surrounding context.

md
| 连接 | 服务地址 | 认证 |
| --- | --- | --- |
| API Key MCP | `https://api.readgzh.site/mcp-server` | 在请求头传入 ReadGZH API Key；匿名使用受共享 IP 配额限制 |
| OAuth MCP | `https://jhnnmmwgdrquwjytvvwu.supabase.co/functions/v1/mcp` | 支持远程 MCP 与 OAuth 的客户端中登录并授权；首次抓取前需在控制台创建有效 API Key |

API Key 连接的配置示例（具体配置位置以客户端说明为准）：

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 40)May include surrounding context.

md
| 连接 | 服务地址 | 认证 |
| --- | --- | --- |
| API Key MCP | `https://api.readgzh.site/mcp-server` | 在请求头传入 ReadGZH API Key；匿名使用受共享 IP 配额限制 |
| OAuth MCP | `https://jhnnmmwgdrquwjytvvwu.supabase.co/functions/v1/mcp` | 支持远程 MCP 与 OAuth 的客户端中登录并授权；首次抓取前需在控制台创建有效 API Key |

API Key 连接的配置示例（具体配置位置以客户端说明为准）：

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 70)May include surrounding context.

md
| 连接 | 服务地址 | 认证 |
| --- | --- | --- |
| API Key MCP | `https://api.readgzh.site/mcp-server` | 在请求头传入 ReadGZH API Key；匿名使用受共享 IP 配额限制 |
| OAuth MCP | `https://jhnnmmwgdrquwjytvvwu.supabase.co/functions/v1/mcp` | 支持远程 MCP 与 OAuth 的客户端中登录并授权；首次抓取前需在控制台创建有效 API Key |

API Key 连接的配置示例（具体配置位置以客户端说明为准）：

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The API explicitly states that new article URLs are scraped, cached, and later searchable/listable, but the specification does not clearly warn users that submitting a URL can cause persistent storage and broader discoverability of that content through other endpoints. This creates a privacy and data-handling risk because users or agents may submit links assuming ephemeral retrieval, while the service actually republishes metadata and cached content.

Content

No source excerpt is available for this finding.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
openapi.yaml:9