ClawHub
Back to skill

Security audit

Apple TV

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Apple TV remote-control skill with disclosed device-control and credential-handling behavior, but users should be aware it can change TV state.

Install this only if you want your agent to act as a remote for your Apple TV. Protect the appletv.json credential file, verify the pyatv install source, and consider requiring confirmation for disruptive actions such as power control, volume changes, navigation, or launching apps.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill clearly instructs use of shell commands and a local Python script, yet it declares no permissions. That mismatch can bypass user/admin expectations about what the skill is allowed to do and increases risk because the skill can invoke local executables and interact with the networked Apple TV without explicit permission gating.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The phrase "what's playing" is ambiguous and not device-specific, so it may activate during normal media-related conversation. Because this skill can control a real device, ambiguous triggers expand the attack surface for accidental or contextually manipulated activation, especially in shared environments.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The phrase "what's playing" is ambiguous and not device-specific, so it may activate during normal media-related conversation. Because this skill can control a real device, ambiguous triggers expand the attack surface for accidental or contextually manipulated activation, especially in shared environments.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.