ClawHub
Back to skill

Security audit

Mac Health Check

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local Mac telemetry helper whose shell use is disclosed and aligned with checking system health.

Install this only if you want an agent to run local macmon commands to read current Mac telemetry. Be aware that the included wrapper may invoke zsh as a login shell, so your shell startup files and PATH can influence what runs.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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 (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill invokes shell commands and reads local files/stdin, but it does not declare any explicit tool scope such as allowed tools or permissions. That creates an authorization gap: an agent/runtime may permit broader execution than reviewers or users expect, increasing the chance of unintended command execution or file access through this skill's wrapper scripts and Python entrypoints.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/macmon_status.py (reported line 28)May include surrounding context.

python
cmd = [binary, "pipe", "-s", "1", "-i", str(interval_ms)]

    try:
        proc = subprocess.run(cmd, capture_output=True, text=True, check=True, timeout=15)
    except FileNotFoundError:
        proc = run_macmon_via_login_shell(interval_ms)
    except subprocess.TimeoutExpired as exc:

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
90% confidence
Finding

This fallback executes macmon through zsh -lic, which launches a login shell and causes shell startup files and the user's environment to influence execution. Although the binary path is shell-quoted and interval_ms is coerced to int, invoking a login shell materially expands the attack surface: compromised shell init files, aliases/functions, or environment manipulation could trigger unintended code execution whenever the skill runs.

Content

Scanner excerpt · scripts/macmon_status.py (reported line 58)May include surrounding context.

python
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,