shipping-price-monitor

• Outcome: Review
• Latest audit: May 29, 2026 at 9:27 PM UTC
• Version:
  1.0.0

Overview

The skill mostly matches its shipping-price alert purpose, but it can automatically send route and pricing data to chat services and defaults OpenClaw messages to a named recipient.

Review before installing. Confirm or change the OpenClaw recipient before enabling monitoring, use a dedicated watch folder with only intended spreadsheets, and treat configured webhook URLs as secrets. Prefer known WeCom/Feishu webhook domains and rotate any webhook that may have been exposed.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 81% confidence
• Finding: The skill documentation clearly describes file access, local configuration changes, and outbound network messaging, but no permissions are declared. This creates a transparency and consent problem: a user or platform may invoke a skill that can read local files, write config/history data, and transmit information externally without an explicit permission boundary.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 88% confidence
• Finding: The declared description frames the skill as simple price monitoring, but the body adds broader capabilities: external messaging to Feishu/WeCom, long-connection delivery via OpenClaw, persistent config/rule editing, and command-style control operations. This mismatch increases the risk that users or reviewers underestimate the skill's ability to exfiltrate data, alter local state, or perform actions beyond passive analysis.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The skill advertises automatic notification delivery over OpenClaw long connection and webhook channels, but does not provide an explicit warning that shipping data derived from monitored Excel files may be sent to external services. In this context, route, carrier, pricing, and schedule data may be commercially sensitive, so silent outbound transmission creates a real confidentiality risk.

Missing User Warnings

Medium

• Confidence: 86% confidence
• Finding: Webhook secrets are written in plaintext to config/settings.yaml, creating a credential-at-rest exposure if the skill directory is readable by other local users, accidentally committed, or included in backups/log bundles. Because these webhooks can often post messages or trigger actions in enterprise chat systems, disclosure can enable unauthorized messaging or alert spoofing.

VirusTotal

60/60 vendors flagged this skill as clean.