Back to skill

Security audit

Gui Tool

Security checks for vulnerabilities and agentic risk

Overview

This GUI automation skill is openly described, but it gives broad screen-viewing and click/type control without safety limits for sensitive apps or actions.

Install only if you want an agent to control desktop applications. Before use, keep sensitive windows closed and require explicit confirmation for form submissions, account changes, purchases, password fields, messages, deletes, or system setting changes.

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

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description is broadly worded to trigger on almost any need to 'see the screen,' 'type into applications,' or 'automate any GUI interaction,' which can cause over-invocation of a highly privileged GUI automation tool. Because this tool can inspect screens, switch windows, click UI elements, and type text, broad activation increases the chance of unintended interaction with sensitive applications or data.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill documentation provides operational instructions for taking screenshots, raising windows, clicking, and typing, but omits any warning about privacy, sensitive on-screen data, or system-impacting actions. In context, this is dangerous because GUI automation can expose confidential information and perform irreversible actions in arbitrary applications without reminding the operator to obtain confirmation or avoid sensitive contexts.

Content

No source excerpt is available for this finding.