ClawHub
Back to skill

Security audit

mac-node-snapshot

Security checks for vulnerabilities and agentic risk

Overview

This skill performs a local macOS screen capture workflow that matches its stated purpose, but users should remember it saves screen contents to temporary files.

Install only if you are comfortable with an agent capturing the visible screen and saving a short MP4 plus PNG locally under the skill's tmp directory. Before using it, close or hide private windows, and delete the temporary capture files afterward if you do not need to keep them.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explains how to capture the screen and save output files, but it does not prominently warn that it records screen contents and writes both video and image artifacts to disk. Because screen contents often include highly sensitive information, lack of notice undermines informed consent and may lead to unintended retention of private data in temporary files.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger phrases are broad enough to activate on common requests like 'Take a screenshot' or 'What is on my screen?', causing the skill to capture sensitive on-screen content with little contextual friction. In a screen-capture skill, broad activation increases the chance of collecting credentials, messages, documents, or other private data when the user did not explicitly consent to this specific capture-and-save workflow.

Static analysis

No suspicious patterns detected.