ClawHub
Back to skill

Security audit

Matter CLI

Security checks across malware telemetry and agentic risk

Overview

This Matter reading-app skill appears purpose-aligned, but it can read and change a user’s saved-reading library.

Install if you want an assistant to manage Matter on your behalf. Be careful with broad requests about your inbox, highlights, or reading list, and confirm before archive, tag, or save operations if you do not want accidental library changes.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger list is broad enough to match common, non-specific phrases like 'reading list', 'inbox', 'highlights', and 'Matter', which can cause the skill to activate in situations the user did not intend. Because this skill can access and modify a user's reading library, overbroad activation increases the chance of unintended data exposure or unintended actions being proposed or executed in the wrong conversational context.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill description advertises write capabilities such as tagging, archiving, and saving URLs without clearly warning that these operations modify user data. In an agent setting, that omission can lead to users or orchestrators invoking state-changing commands without explicit awareness or confirmation, resulting in accidental library changes.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.