ClawHub
Back to skill

Security audit

Smart Leaner

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed learning assistant that keeps local study notes and preferences, with no executable code or hidden data access found.

Install this only if you want a study assistant that stores local notes, quiz results, review plans, and learning preferences under smart-learner/. Avoid using it on sensitive documents unless you are comfortable with study notes being created from them, and use explicit wording when you want a one-off answer without saving progress.

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

High
Confidence
96% confidence
Finding
The trigger list includes broad everyday phrases such as "what is", "review", "summarize", and "analyze this", which can cause the skill to activate unintentionally during unrelated conversations. Because the skill has read/write access and persistent memory behavior, accidental activation can lead to unexpected data collection, file creation, or preference updates without the user clearly intending to invoke the skill.

Vague Triggers

High
Confidence
95% confidence
Finding
Semantic-intent activation in any language is insufficiently bounded and expands the activation surface far beyond the explicit trigger list. This makes it difficult for users to predict when the skill is active, increasing the risk of unsolicited memory reads, note generation, and persistent logging behaviors across normal multilingual conversation.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill description emphasizes persistent storage of learning history, preferences, and session-derived updates, but does not clearly warn users up front about retention, scope, and lifecycle of that data. This creates a privacy transparency problem: users may disclose sensitive educational, professional, or personal material without understanding it will be stored across sessions.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.