Back to skill

Security audit

Web 测试用例生成器

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Chinese web-page test-case generator with minor consent and scoping caveats but no evidence of hidden or malicious behavior.

Before installing, understand that this skill may open and inspect web pages you provide and may save generated test cases as Markdown and CSV files. Use caution on authenticated or private business pages, and ask the agent to confirm filenames and locations before writing outputs.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger conditions are broad enough to match ordinary requests for help writing test cases, which can cause the skill to activate outside its intended scope. In this skill, unintended activation may lead the agent to open supplied URLs and inspect live pages when the user may only have wanted generic advice, increasing the chance of unnecessary browsing or interaction with untrusted sites.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill specifies creating Markdown and CSV output files but does not clearly warn the user before writing files. This can lead to unexpected filesystem side effects, accidental overwrites, or persistence of potentially sensitive page-derived content without explicit user awareness or consent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The description and examples are entirely in Chinese, and the skill does not indicate that language selection is optional or user-configurable. This can violate language/locale policy expectations when a skill implicitly forces a specific language without opt-in.

Content

No source excerpt is available for this finding.