Aibrary Foryou Topic

Security checks across malware telemetry and agentic risk

Overview

This is a simple instruction-only skill for personalized book-topic recommendations and does not request code execution, credentials, file access, persistence, or external data transfer.

This appears safe to install. The main consideration is privacy: because recommendations can be based on career, goals, interests, and recent learning activity, only share personal context you are comfortable using for recommendation generation.

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 (1)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The manifest description contains broad activation language such as 'use when the user wants personalized topic suggestions,' 'asks what should I learn today,' and 'proactively suggest this when the user seems undecided,' which can match common conversational intents and cause the skill to trigger too often. Over-broad routing increases the chance that user context is unnecessarily sent into this skill, leading to unintended invocation, irrelevant responses, and possible privacy over-collection if profile or learning-history data is used without clear need.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal