ClawHub
Back to skill

Security audit

自动化测试助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward automated-testing assistant; the flagged network call is an example API test, not hidden data transfer by the skill itself.

Install this if you want Chinese-language guidance for generating and improving automated tests. Review generated tests before running them, especially API, CI, Appium, and performance-test examples, so they target only your intended test systems and do not use real credentials or production data.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description includes very broad trigger phrases such as '写测试', '测试脚本', 'unit test', and other generic testing terms, which can cause the skill to activate in many ordinary conversations beyond a clearly scoped intent. Over-broad activation increases the chance of unintended routing, prompt capture, or the skill influencing conversations where it was not explicitly requested, which is a genuine security and safety boundary issue for agent skills.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill content is written entirely in Chinese and does not instruct the agent to respect the user's language preference, which can force output in a language the user did not request. While not a direct code-execution issue, this is a real policy and usability weakness because it can mislead users, reduce transparency, and increase the risk that important testing or security guidance is misunderstood.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% 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 304)May include surrounding context.

md
}
        
        # Act
        response = requests.post(self.api_url, json=payload)
        
        # Assert
        assert response.status_code == 201

Static analysis

No suspicious patterns detected.