Back to skill

Security audit

视频封面设计助手

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language video cover design helper with no evident hidden access, persistence, or data exfiltration behavior.

Reasonable to install for Chinese-language short-video cover ideation. Be aware that the bundled Python helper may fail until the undefined platform_config bug is fixed, and it does not currently offer non-Chinese output controls.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This file’s natural-language descriptions and generated output are exclusively in Chinese, and there is no indication that users can opt into another language or that the skill is intentionally limited to a Chinese-speaking context. That can violate language/locale policy when a skill effectively forces a specific language without user choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The templates and formatted output shown to users are all hard-coded in Chinese, and the code does not provide any mechanism to select another language. This means the skill enforces a single language in user-facing behavior rather than offering a documented choice or justified region-specific constraint.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

L229-L230 表明该函数用于“生成构图建议”,并且其签名显示会基于 platform 生成结果,但 L241 实际读取的是未在函数内定义、也未作为参数传入的 platform_config。也就是说,代码表达的意图是按平台生成构图建议,但实现并未按所声明的输入工作,反而会在运行时出错。

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.