ClawHub
Back to skill

Security audit

wsl-screenshot

Security checks for vulnerabilities and agentic risk

Overview

This is a narrow WSL screenshot helper, but users should be careful because screenshots can reveal private on-screen information.

Install only if you want the agent to capture your full primary Windows screen from WSL. Before asking it to send a screenshot, close or hide private windows and review the saved image when possible; also note that files are left in the configured Pictures folder.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly instructs taking a screenshot and immediately sending the latest captured image to the user, but provides no warning that screenshots can contain sensitive on-screen content such as passwords, messages, documents, browser tabs, or unrelated user data. In this context, the omission materially increases privacy and data-exposure risk because the functionality is specifically designed to capture the full primary screen and exfiltrate the image via a message tool.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.