ClawHub
Back to skill

Security audit

Lingxing

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Lingxing connector that runs scoped OOMOL CLI actions against a connected account, with sensible confirmation guidance for state-changing actions.

Install only if you intend to let your agent access your connected Lingxing ERP account through OOMOL. Review any `[write]` action carefully before approving it, especially `list_order_profit`, whose documentation is inconsistent with its write tag. Only run the CLI installer and account connection steps when you expect to set up OOMOL access.

SkillSpector

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
`list_order_profit` is described as a read/list operation but is simultaneously tagged `[write]`, creating a dangerous mismatch between the apparent semantics and the declared safety class. That ambiguity can cause an agent or user to treat the action as harmless when it may mutate state, or conversely normalize incorrect safety metadata, increasing the chance of unintended writes in a finance-related ERP context.

Vague Triggers

Medium
Confidence
86% confidence
Finding
The description says to use this skill for ANY Lingxing request and instead of calling the API directly, which is an overly broad routing instruction. In an agentic system, that can cause the skill to be invoked for loosely related mentions, expanding the chance of unnecessary access to enterprise ERP data or accidental execution of sensitive actions in contexts where the user did not intend to use this connector.

Static analysis

No suspicious patterns detected.