Back to skill

Security audit

Mac Health Check

Security checks across malware telemetry 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

By NVIDIA
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
return subprocess.run( [shell, "-lic", shell_cmd], capture_output=True, text=True, check=True, timeout=20, )

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.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal