ClawHub
Back to skill

Security audit

Plex Media Remote

Security checks for vulnerabilities and agentic risk

Overview

This Plex skill does what it says: it uses a Plex token to search library data, show playback information, and control Plex clients, with privacy cautions but no evidence of hidden or malicious behavior.

Install only if you are comfortable giving the agent a Plex token that can read your Plex library, viewing activity, active clients, and control playback devices. Review mutating actions like play, pause, resume, and stop before they run, and delete the temp file plex_media_cache.json if your local media metadata is sensitive.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill declares environment variables and describes temporary-file caching, but it does not declare corresponding permissions despite clearly requiring env, file_read, and file_write capabilities. This creates a transparency and least-privilege problem: a runner or reviewer may underestimate what the skill can access, including sensitive Plex credentials and cached media/library data.

Missing User Warnings

Medium
Confidence
80% confidence
Finding
The skill exposes session, client, and continue-watching data, including usernames, device names, device addresses, playback state, and viewing activity, with no access control, minimization, or warning. In an agent context, this can disclose sensitive household/user behavior and internal network information to any caller permitted to invoke the skill.

Static analysis

No suspicious patterns detected.