Back to skill

Security audit

scene-replace

Security checks for vulnerabilities and agentic risk

Overview

The skill is rated benign with medium confidence: the scanners found no AIG issues, while Skillspector flagged file deletion and an external upload example that are considered purpose-related, but its analysis was partial.

The verdict is benign, but confidence is medium and Skillspector's analysis was partial because several referenced paths were not included. Before installing, consider whether you are comfortable with the documented image upload destination and local temporary-file cleanup; the scan does not establish that the incomplete evidence is risk-free.

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 (2)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
91% confidence
Finding

The supplied code only deletes a local JSON file; it does not call Flyelep AI or perform image-background replacement. Temporary-file cleanup could support the declared workflow, but no such workflow or connection is present in the supplied chunk.

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 129)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