ClawHub
Back to skill

Security audit

Windows Screenshot

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward Windows screenshot skill that saves a user-invoked screen capture locally, with privacy caution warranted because screenshots can contain sensitive information.

Install only if you want a Windows-only tool that captures the current primary screen and saves it as a local PNG. Review your screen before running it, set OPENCLAW_MEDIA_DIR if you want a different save location, and delete saved screenshots when they are no longer needed.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The README clearly states that the skill captures screenshots, but it does not explicitly warn users that executing it will capture the current screen contents and persist the image to disk. This is security-relevant because screenshots may contain sensitive data such as credentials, messages, customer data, or internal documents, and silent local storage increases the chance of unintended exposure.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The script captures the full primary screen and writes it to disk without any user notice, consent, or confirmation. In an agent skill context, this can expose sensitive on-screen data such as credentials, private messages, tokens, or customer information, especially because the file is silently saved to a predictable user directory.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The user-facing instructions, usage guidance, and safety statement are presented only in Chinese. Under the policy, forcing a specific language without user opt-in or a documented, justified locale constraint is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
98% confidence
Finding

The inline comment at L06 says the environment variable is used for cross-platform compatibility, but the script clearly depends on Windows-specific .NET APIs such as System.Windows.Forms.Screen and Graphics.CopyFromScreen. In reality, L07 only reads an environment variable to select the media output path, so the comment actively misstates the purpose and effect of that code.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.