Back to skill

Security audit

image-enlarge

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marked this skill suspicious because scanners reported public third-party image hosting without a privacy warning and a possible mismatch between its stated purpose and demonstrated behavior; analysis was partial.

Consider the privacy implications before installing, especially if you might process sensitive images: the scanner reports public third-party links and no upfront privacy warning. The analysis was marked partial because some local references could not be resolved, so the evidence is incomplete; the suspicious verdict is a review warning, not a claim that the author is malicious.

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 API interaction or image-processing operation. Deleting a temporary payload file could support a larger workflow, but no such workflow is present in the supplied chunk; its only demonstrated behavior does not implement the declared purpose.

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

The skill directs the agent to upload user-provided local images to third-party storage and obtain publicly accessible, unsigned URLs without first requiring a user-facing privacy disclosure or consent to public hosting. External processing is consistent with the skill's purpose, but users may not expect public accessibility, 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 146)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