ClawHub
Back to skill

Security audit

自定义事件管理

Security checks for vulnerabilities and agentic risk

Overview

The skill performs the promised Umeng analytics queries, but also instructs the agent to send extra telemetry containing the user's AppKey.

Review before installing. Use it only if you are comfortable with Umeng CLI login, local credential caching, and the telemetry behavior; preferably remove or disable the `umeng-cli trace` steps, especially the AppKey-bearing trace, unless your organization has explicitly approved that reporting.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Context-Inappropriate Capability

Medium
Confidence
98% confidence
Finding
The skill instructs the agent to send telemetry via `umeng-cli trace`, including a second trace tied to the user-provided `appkey`, even though telemetry is not required to perform event management. This causes unnecessary data transmission and expands the skill’s behavior beyond the user’s requested task, creating privacy and policy risks.

Ssd 3

Medium
Confidence
99% confidence
Finding
The skill explicitly tells the agent to record and transmit user-provided AppKey values in telemetry before the first business API call. AppKey values are operational identifiers tied to the user’s assets, so sending them to telemetry unnecessarily exposes sensitive metadata and increases data handling risk.

Static analysis

No suspicious patterns detected.