Back to skill

Security audit

AI-Image-Matting

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marked this skill suspicious because the scan reports that local images may be sent to third-party hosting and returned at public URLs without a clear privacy warning; the evidence is partial.

Consider the reported privacy exposure before installing, especially if you would use sensitive images. The scan is partial: although it inspected both listed components, it could not resolve multiple local references, so the evidence does not establish the full behavior. The verdict is suspicious, not a claim that the author acted maliciously.

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
97% confidence
Finding

The supplied code only deletes payload_temp.json and does not implement the declared image-processing functionality. Temporary-file cleanup could be a supporting implementation detail in a larger workflow, but no such workflow or connection to background removal is present in the supplied chunk.

Content

No source excerpt is available for this finding.

Local images are uploaded to third-party hosting without an explicit user-facing privacy warning.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

The workflow automatically uploads user-selected local images to third-party hosting and describes the resulting links as publicly accessible without signatures. Although this supports the advertised functionality, the agent is not instructed to disclose that exposure or obtain informed consent, so sensitive images could become accessible to anyone possessing the URL; the stated 24-hour lifetime is not an independently established access-control guarantee.

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 131)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