Back to skill

Security audit

intelligent-extension

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this image-extension skill suspicious because it reports uploading local images to a third-party service and does not require a privacy warning or confirmation; the scan evidence is incomplete.

Before installing, consider whether you are comfortable sending local images to the third-party service and having them hosted at publicly accessible links. The scanner says the claimed 24-hour expiry is not verified, and the scan was marked partial because some 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
94% confidence
Finding

The supplied chunk only deletes a file; it contains no image processing, Flyelep API interaction, batch handling, or aspect-ratio configuration. Temporary-file cleanup could support the declared workflow, but no such connection is established in the supplied code.

Content

No source excerpt is available for this finding.

The workflow uploads local images to a third-party service without requiring a user-facing privacy warning.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The local-file workflow uploads user images to third-party storage and produces unsigned, publicly accessible URLs without requiring a user-facing disclosure or confirmation of that exposure. Although remote image processing is the stated purpose, providing a local path does not necessarily imply informed agreement to public-link hosting, 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