Back to skill

Security audit

image-clarity-enhance

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a benign verdict with medium confidence: the described image-enhancement purpose is broadly supported, though a partial scan flagged an external upload and a possible mismatch between the stated purpose and a temporary-file cleanup command.

Before installing, check that you are comfortable sending images to the Flyelep service and using its API key. The verdict is benign, but the scan was partial because some referenced paths were not present in the bundled artifact, and the cleanup command's relationship to the main function was not shown.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

所提供代码的唯一行为是删除 payload_temp.json,而不是增强图片。临时文件清理可以是合理的辅助实现细节,但此代码片段没有展示该文件与图片增强流程的关联,也没有实现所声明的核心功能,因此就所提供片段而言存在用途不匹配。

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

删除临时文件可能是正常工作流的辅助清理步骤,本身不必然构成未声明能力。但所提供的代码仅包含删除命令,没有任何图片处理或接口调用,因此就该代码块而言,其实际行为与声明的主要用途不符。

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 145)May include surrounding context.

判断成功只看 code,业务失败时 HTTP 状态码仍是 200,code 为 500 或 9999,原因在 msg 里。

bash
# Windows/PowerShell(用 curl.exe,PowerShell 里的 curl 是 Invoke-WebRequest 的别名)
curl.exe -X POST "https://www.flyelep.cn/prod-api/poster-design/api/v1/file/upload" -H "secretKey: 你的密钥" --max-time 120 -F "file=@C:/path/to/product.png"

# macOS/Linux