Back to skill

Security audit

Google全家桶入口

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Google services launcher that reads its bundled catalog and opens selected official Google or YouTube URLs.

Install this if you want a Chinese-language shortcut menu for Google services. Be aware that the short name "g" may be easy to invoke unintentionally, and opening items will navigate your browser to Google or YouTube services where normal account/session behavior applies.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file describes the skill as "g" and says to enable the skill in ClawHub.ai, but it does not define when the skill should activate, what exact trigger phrases are valid, or any exclusion conditions. A single-letter name is especially prone to accidental overlap, making invocation scope overly broad and unclear.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code presents all user-facing prompts and status messages in Chinese, including the title, menu, input prompts, and error messages. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly documented and justified, which is not present in this file.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This JSON manifest uses Chinese-language descriptions and category labels throughout, with no indication that the skill is region-specific or that users can choose another language. That creates a natural-language locale constraint that may violate organizational language-choice policy for generally applicable skills.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

Natural-language policy issues include forcing a specific language without user opt-in. Here, the descriptive content is presented in Chinese only, and there is no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking audience.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.