ClawHub
Back to skill

Security audit

airplay-screen

Security checks for vulnerabilities and agentic risk

Overview

The skill’s setup and phone-screen access fit its stated purpose, with disclosed controls and manageable privacy and dependency risks.

Only mirror content you are comfortable sharing with your AI service; local reception does not guarantee local AI processing. Use a trusted network, stop mirroring when finished, manage saved screenshots, and consider pinning reviewed dependency versions.

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

MCP server dependency without pinned version: 'pip install --upgrade airplay-mcp'.

Low
Category
MCP Rug Pull
Confidence
97% confidence
Finding

The unpinned upgrade installs whichever airplay-mcp release is current, so a compromised or malicious future release could execute code with the installing user's privileges. Registering that executable as an MCP server and giving it access to mirrored phone screens increases the potential impact to sensitive screen disclosure and host compromise; the skill's local-only assurances do not constrain a compromised dependency.

Content

No source excerpt is available for this finding.