ClawHub
Back to skill

Security audit

BaseLinker

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed BaseLinker connector helper, with no evidence of hidden data theft, destructive behavior, or deceptive execution.

Install only if you intend to let the agent use your OOMOL-connected BaseLinker account. Review the oo CLI installer and account connection, and treat order data as business-sensitive even though the current listed actions are read-oriented.

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
90% confidence
Finding
The action list labels `list_order_events` and `list_order_statuses` as `[write]` even though their names and descriptions indicate read-only listing operations. This misclassification can cause the agent to apply the wrong safety policy: either prompting unnecessarily and creating operator confusion, or more importantly normalizing incorrect safety labels so future truly mutating actions may be misunderstood and approved under inconsistent assumptions.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger text says to use this skill for "ANY BaseLinker request" and whenever a task merely "involves BaseLinker," which is broader than necessary. An overly broad scope can cause unintended invocation in loosely related contexts, increasing the chance the agent runs connector commands or requests schemas when the user only wanted discussion, planning, or a different system, potentially exposing connected-account data or causing accidental operations.

Static analysis

No suspicious patterns detected.