ClawHub
Back to skill

Security audit

ShipStation

Security checks across malware telemetry and agentic risk

Overview

This ShipStation skill is a disclosed OOMOL connector for reading ShipStation purchase-order and inventory data, with minor documentation issues but no evidence of hidden or malicious behavior.

Install only if you trust OOMOL and are comfortable connecting ShipStation through its oo CLI. Review any proposed oo connector action and payload before approval, especially because the description is broader than the listed read-oriented actions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Intent-Code Divergence

Medium
Confidence
95% confidence
Finding
The action list labels `get_purchase_order` as `[write]` even though its description says it retrieves data. Misclassifying a read action as a write undermines the safety model described elsewhere in the skill and can cause the agent or user to make incorrect trust and confirmation decisions. In a connector skill, inaccurate action semantics are dangerous because they affect whether operations are run automatically or gated behind approval.

Vague Triggers

Medium
Confidence
86% confidence
Finding
The description says to use this skill for "ANY ShipStation request" and instead of calling the API directly, which is an overly broad invocation trigger. This can cause the agent to route all ShipStation-related tasks through this skill without considering least privilege, narrower alternatives, or whether the skill's documented safety constraints are appropriate for the task. Because the skill supports both read and state-changing operations, overbroad routing increases the chance of unintended use in sensitive workflows.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.