ClawHub
Back to skill

Security audit

GSC Connect - Google Search Console

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed read-only Google Search Console connector guide with no embedded code or hidden behavior found.

Before installing, confirm you trust the YUSIHK remote MCP service and are comfortable granting it read-only access to your Google Search Console data. Do not paste passwords, tokens, cookies, client secrets, or authorization codes into chat or configuration fields.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Credential Access

High
Category
Privilege Escalation
Content
- Traditional Chinese documentation: [`https://gsc.yusihk.com/zh-hant/docs`](https://gsc.yusihk.com/zh-hant/docs)
- YUSIHK product guide: [`https://yusihk.com/en/gsc-connect-codex-plugin-google-search-console/`](https://yusihk.com/en/gsc-connect-codex-plugin-google-search-console/)

The service requests read-only Search Console access. Never ask the user for a Google password, OAuth client secret, access token, refresh token, cookie, or authorization code.

## Configure OpenClaw
Confidence
70% confidence
Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

MCP Config Access

High
Category
Agent Snooping
Content
4. Reload MCP and start a new task if the current task does not refresh its tool list.
5. Do not claim that live GSC data was accessed until the connector exposes the tools.

On older OpenClaw releases that do not have `status` or `doctor`, use `openclaw mcp show google-search-console` to confirm the saved definition, then restart OpenClaw and inspect the MCP settings screen.

## Select a property first
Confidence
90% confidence
Finding
Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
- Traditional Chinese documentation: [`https://gsc.yusihk.com/zh-hant/docs`](https://gsc.yusihk.com/zh-hant/docs)
- YUSIHK product guide: [`https://yusihk.com/en/gsc-connect-codex-plugin-google-search-console/`](https://yusihk.com/en/gsc-connect-codex-plugin-google-search-console/)

The service requests read-only Search Console access. Never ask the user for a Google password, OAuth client secret, access token, refresh token, cookie, or authorization code.

## Configure OpenClaw
Confidence
80% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Natural-Language Policy Violations

Low
Confidence
83% confidence
Finding
The example requests are presented in Chinese, and there is no accompanying statement that the skill should match the user's preferred language or offer a language choice. Under the policy rule, forcing or implicitly defaulting to a specific language without opt-in can be a natural-language policy concern.

Static analysis

No suspicious patterns detected.