Back to skill

Security audit

自动刷新技能

Security checks for vulnerabilities and agentic risk

Overview

This is a simple auto-refresh automation skill, but users should be careful because repeated clicks or keystrokes can affect the active window.

Install only if you want a Chinese-language helper for timed browser refreshes or repeated UI input. Before using click or key actions, confirm the target window and page are active, avoid production or privileged workflows, and make sure you can stop the automation quickly.

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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly supports automated click and key actions, which can trigger unintended UI behavior, destructive shortcuts, repeated form submissions, or data loss if used in the wrong window or context. Because the description provides examples for synthetic input but does not warn users about focus, target verification, or system impact, it increases the chance of unsafe operation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The natural-language description and usage guidance are written in Chinese, which effectively forces a specific language for users without any opt-in or alternative. The policy calls for flagging language or locale constraints unless the skill offers a choice or clearly documents a justified region-specific limitation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.