ClawHub
Back to skill

Security audit

Breakdown Connectivity

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Breakdown connectivity helper, but users should understand that setup can install an app, persist MCP configuration, and expose local network evidence to Breakdown tools.

Install this only if you want agents to use Breakdown for macOS network troubleshooting. Before running setup commands, review whether you want the app installed, the Breakdown MCP bridge added to Codex or Claude Code, and network evidence or cloud-backed analysis used for the troubleshooting task.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill instructs the agent to run local shell commands such as ./scripts/setup-breakdown.sh install, open-app, and configuration actions, but it does not declare corresponding permissions. That mismatch can cause the agent or user to invoke shell-capable behavior without clear upfront authorization boundaries, increasing the risk of unexpected local changes, software installation, or configuration modification.

Vague Triggers

Medium
Confidence
76% confidence
Finding
The activation text is broad enough to match many ordinary flaky-task or readiness scenarios, which can cause the skill to be invoked more often than necessary. Because this skill includes installation, app launching, MCP configuration, and shell-based setup guidance, overbroad triggering expands the chances of unnecessary execution of impactful local actions.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The default prompt activates the skill for a very broad class of 'connectivity problem' scenarios without clear guardrails, user-confirmation requirements, or scope limits. In an agent environment, this can cause over-triggering and unnecessary invocation of a diagnostic capability that may inspect network state, endpoints, or related system context, increasing the chance of unintended data exposure or disruptive actions.

Static analysis

No suspicious patterns detected.