ClawHub
Back to skill

Security audit

Mac Health Check

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Mac health checker that runs the local macmon tool and summarizes one telemetry snapshot.

Install this only if you are comfortable letting the agent run local macmon commands on your Mac. The main practical risk is your local shell/PATH setup: the compatibility fallback may run through zsh login-shell startup files, so use it in a trusted local environment and verify the macmon Homebrew package you intend to use.

SkillSpector

Vulnerability Patterns
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • 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 (2)

subprocess module call

Medium
Category
Dangerous Code Execution
Content
shell_cmd = f"{shlex.quote(binary)} pipe -s 1 -i {int(interval_ms)}"

    try:
        return subprocess.run(
            [shell, "-lic", shell_cmd],
            capture_output=True,
            text=True,
Confidence
92% confidence
Finding
The fallback executes macmon through `zsh -lic`, which evaluates a command string inside a login shell. Although the binary path is shell-quoted and interval_ms is cast to int, invoking a login shell loads shell startup files and trusts PATH resolution for both zsh and macmon, increasing exposure to environment- or profile-based command hijacking if the skill runs in an untrusted local context.

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill invokes shell commands and reads local files/stdin, but does not declare any permissions to reflect those capabilities. That mismatch is a real security issue because users and the platform cannot accurately assess or constrain what the skill will access or execute, especially since it runs wrappers like `bash {baseDir}/bin/macmon-safe.sh` and reads arbitrary input files such as `/tmp/macmon.jsonl` or stdin.

Static analysis

No suspicious patterns detected.