ClawHub
Back to skill

Security audit

BT Panel MCP

Security checks for vulnerabilities and agentic risk

Overview

This skill presents itself partly as read-oriented, but it can invoke broad BT Panel server-management tools that may make high-impact changes.

Review this before installing if your BT Panel connection has production or administrative privileges. Use it only where explicit confirmation for every state-changing or destructive BT Panel action is acceptable, and prefer a narrower read-only skill for simple discovery or reporting tasks.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Description-Behavior Mismatch

High
Confidence
98% confidence
Finding
The manifest and description position the skill as suitable for 'searching and reading data', but the documented interface includes a generic `call_tool` path that can invoke write, destructive, command-execution, firewall, and file-modification operations. This mismatch can cause an agent or user to trust the skill as read-only and invoke it in lower-scrutiny contexts, enabling unintended high-risk actions against BT Panel-managed infrastructure.

Context-Inappropriate Capability

High
Confidence
97% confidence
Finding
`call_tool` exposes an effectively arbitrary server-management execution surface through BT Panel MCP, including the possibility of command execution and other sensitive operations, while the skill's stated purpose is read/search oriented. A generic passthrough like this greatly expands attack surface and allows the skill to reach capabilities far beyond what a consumer of the manifest would reasonably expect.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger language says to use this skill for 'ANY BT Panel MCP request,' which is overly broad and can route unrelated or higher-risk BT Panel tasks through this skill by default. In context, that broad routing is more dangerous because the skill is not actually limited to reads and includes a generic tool invocation path that may expose privileged server operations.

Static analysis

No suspicious patterns detected.