ClawHub
Back to skill

Security audit

xcodebuildmcp

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Xcode automation skill with powerful but purpose-aligned build, device, media, log, and debugging capabilities.

Install this only if you want an agent to drive Xcode workflows. Prefer pinning and reviewing the external XcodeBuildMCP package instead of relying on `latest`, use test simulators/devices when possible, and confirm before allowing screenshots, logs, video recording, physical-device installs, simulator erase/clean actions, or LLDB commands.

SkillSpector

By NVIDIA
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 (2)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The workflow explicitly encourages screenshots for verification and elsewhere documents video recording and simulator log capture, but provides no warning that these features may capture sensitive application content, credentials, tokens, personal data, or developer environment information. In a build/test/debugging skill, these collection features are legitimate, but the lack of disclosure and handling guidance increases the chance that an agent will gather or retain sensitive data without user awareness.

Missing User Warnings

Low
Confidence
88% confidence
Finding
The device workflow instructs build, install, and launch actions on a connected physical device without warning that the app will be deployed and executed on real hardware. In this skill context, device deployment is expected functionality, which reduces severity, but users should still be informed because these actions can alter device state, consume resources, prompt trust dialogs, and expose data on non-test devices.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.