Back to skill

Security audit

Control

Security checks for vulnerabilities and agentic risk

Overview

This skill openly provides desktop automation, but its broad activation terms and optional safety controls make it worth manual review before installation.

Review this skill carefully before installing. Use it only in an isolated or low-risk desktop session, keep approval mode enabled for actions, avoid administrator privileges unless truly necessary, and pin/review the Python dependencies before installing them.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:90
Finding

Unpinned Third-Party Python Dependencies

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 90–93
Vulnerability Type: Unpinned dependencies installed from a mutable package index
Risk Level: Medium

Vulnerable Code

bash
pip install pyautogui pillow opencv-python pygetwindow

The same command is repeated at lines 665–668.

Technical Analysis

The installation command does not constrain dependency versions or verify package integrity with cryptographic hashes. Consequently, pip resolves whatever versions are available from the configured package index at installation time, including applicable transitive dependencies.

Python package installation can execute package-controlled build or installation logic. A compromised future release, compromised package-index configuration, dependency-confusion condition, or malicious transitive dependency could therefore result in arbitrary code execution under the installing user's account.

The supply-chain exposure is particularly significant here because the packages support desktop automation, image processing, screenshots, window management, and input control. The project provides no lockfile, hash-verified requirements file, or other reproducible dependency specification.

Attack Path

  1. A user or Agent follows the installation instructions in SKILL.md.
  2. pip queries its configured package index and resolves uncontrolled current versions of the named packages and their transitive dependencies.
  3. An attacker compromises an applicable package release or causes resolution from an untrusted or attacker-controlled index.
  4. The malicious package executes code during installation, build, or subsequent import.
  5. That code runs with the privileges of the user performing the installation and can access resources available to that account.

Impact Assessment

Successful exploitation could provide arbitrary code execution with the installing user's privileges. Depending on the execution environment, this could expose fi ...[truncated 454 chars]

Remediation
View remediation

Remediation Suggestions

  1. Move dependencies into a reviewed requirements or lock file and pin exact versions.
  2. Generate and enforce cryptographic hashes, for example with pip install --require-hashes -r requirements.txt.
  3. Pin and review transitive dependencies as well as direct dependencies.
  4. Install only from an explicitly trusted package index and disable unintended additional indexes.
  5. Perform installation inside an isolated virtual environment or restricted container under a non-administrative account.
  6. Run dependency vulnerability and provenance checks before publishing updates.
  7. Establish a controlled process for periodically reviewing, testing, and updating pinned versions.
  8. Remove or strongly discourage guidance to run the automation environment with administrator privileges unless a narrowly defined operation demonstrably requires it.
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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger keywords are extremely generic ('mouse, automation, advanced, control, desktop'), which makes the skill likely to activate in many unrelated contexts. For a skill that exposes high-risk capabilities like desktop control, keyboard input, screenshots, clipboard access, and command execution, overbroad triggering increases the chance of accidental invocation and unintended privileged actions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

Natural-language policy requires avoiding forced language or locale constraints unless the user can opt in or the restriction is justified. This file presents core descriptive content in Chinese alongside English branding, but does not state that the skill is Chinese-only or offer an alternative language selection.

Content

No source excerpt is available for this finding.