Back to skill

Security audit

image-translate

Security checks for vulnerabilities and agentic risk

Overview

The verdict is suspicious with medium confidence because the scan reports that local images may be uploaded to third-party public storage without a user-facing privacy warning; the scan was partial, so the evidence is incomplete.

Before installing, consider whether you are comfortable sending local images to third-party storage where unsigned public links may be accessible to anyone who has them. The stated 24-hour expiry was not verified. The scan inspected all listed components but marked its analysis partial because several local references could not be resolved, so the evidence is incomplete.

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 (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The code contains no Flyelep AI call, image processing, translation, or translated-image URL output. Removing a temporary payload file could support a larger implementation, but the supplied chunk provides no evidence of that connection and implements only deletion.

Content

No source excerpt is available for this finding.

Local images are automatically uploaded to third-party, publicly accessible storage without a user-facing privacy warning.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

For local inputs, the workflow uploads the image to third-party storage and obtains an unsigned, publicly accessible URL without requiring a user-facing disclosure or informed confirmation. Although external processing is consistent with this translation skill, users may not expect local images containing personal or confidential information to become accessible to anyone holding the URL, and the instruction to treat links as expiring after 24 hours does not establish enforced expiration.

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 154)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