Back to skill

Security audit

product-color-change

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a product image recoloring skill with concerns about unexplained local file deletion and file upload instructions; the verdict is suspicious, meaning review is advised.

Consider holding off until you can verify the Flyelep upload destination is the service you intend to use and understand what image data will be sent. The scan is partial because referenced local paths were missing, so the evidence is incomplete; the reported fixed-file overwrite and deletion risk also merits caution.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied code only deletes a local JSON file; it does not identify products, process images, change colors, or invoke Flyelep AI. Temporary-file cleanup could support such a workflow, but the provided chunk establishes no such connection.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The only supplied operation deletes payload_temp.json, rather than performing the declared product-image recoloring task. Temporary-file cleanup could be a supporting implementation detail, but the supplied code provides no workflow or context establishing that connection.

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 151)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

The Windows workflow overwrites and deletes a fixed local filename without warning about existing-file data loss.

Medium
Category
Output Handling
Confidence
99% confidence
Finding

The Windows instructions write to a predictable payload_temp.json in the current directory without checking whether it already exists, then delete that path after the request. An existing user file could therefore be overwritten and removed; concurrent executions can also interfere with each other's payloads.

Content

No source excerpt is available for this finding.