ClawHub
Back to skill

Security audit

物流查询助手

Security checks across malware telemetry and agentic risk

Overview

This package-tracking skill is mostly purpose-aligned, but it uses an unsafe pattern that asks users to put a Track123 API key directly into the skill file.

Review before installing. Use it only if you are comfortable sending shipment identifiers to Track123, and do not paste an API key into the skill file; use a secure secret store or environment variable instead, and rotate any key that has already been embedded.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Context-Inappropriate Capability

High
Confidence
99% confidence
Finding
The skill explicitly tells the agent to solicit a Track123 API key from the user and then persistently replace the placeholder in the skill file with the real secret. This creates a credential-handling vulnerability because secrets are being collected in-band and stored in skill content, where they may be exposed to logs, other users, later prompts, or unintended reuse.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger conditions are broad enough to activate on common package-related utterances or even arbitrary number strings, increasing the chance the skill runs unintentionally. That can lead to unnecessary third-party transmission of tracking numbers or confusing behavior, especially because the skill is designed to call an external API.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill sends tracking numbers to a third-party API but provides no user warning or consent step before transmission. Tracking numbers can reveal shipment activity, geography, and purchase-related metadata, so silent sharing with an external service creates a privacy and data-governance risk.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
Instructing users to paste an API key into the skill without any credential-handling safeguards encourages unsafe secret disclosure. Combined with the instruction to replace the placeholder in the file, this can permanently embed secrets in prompt content or configuration where they are easier to leak.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.