ClawHub
Back to skill

Security audit

TRMNL Display

Security checks across malware telemetry and agentic risk

Overview

This is a coherent TRMNL display helper that sends user-created display content through the documented TRMNL CLI/webhook flow, with privacy and npm-install cautions but no hidden or incompatible behavior found.

Install this only if you intend to use a TRMNL display or plugin. Treat the custom plugin webhook URL as sensitive, consider pinning or reviewing the npm CLI package instead of always using `@latest`, and ask the agent to preview or validate content before sending anything private, account-related, or visible on a shared display.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill description is broadly scoped enough to match common user requests like showing notifications, updating displays, or generating dashboard content, which increases the chance of accidental activation. Because the skill can ultimately send data to a configured external webhook/device, broad triggering raises the risk of unintended data transmission from otherwise ordinary conversations.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The workflow explicitly directs the agent to send generated content to a device and to provide only minimal confirmation, without requiring a warning that data is being transmitted to an external webhook-backed service. This is dangerous because users may not realize content from the conversation is leaving the local session and being delivered to a third-party endpoint or physical device.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The documentation explicitly exposes personally identifying template variables such as first name, last name, and email without any accompanying privacy, minimization, or access-control guidance. In the context of a skill that generates display content for external devices, this increases the risk that developers will render or transmit PII to screens, webhooks, logs, or third-party content flows without realizing the privacy implications.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.