Ai Intelligent Knowledge Base

• Outcome: Pass
• Latest audit: May 29, 2026, 8:24 PM
• Version:
  1.0.0

Overview

This skill is a coherent enterprise knowledge-base description, but users should verify the remote code it asks them to run and control what documents are indexed.

Before installing, inspect the referenced GitHub repository and requirements, run it in a virtual environment or container, and only index documents approved for this knowledge base. Confirm where embeddings and AI Q&A data are processed, how access controls work, and how indexed content can be deleted.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill markets enterprise knowledge management, semantic search, and AI Q&A over company documents but provides no warning about ingesting confidential, regulated, or proprietary data. In this context, users may upload sensitive internal content without understanding the privacy, access control, retention, or model-exposure risks, which can lead to unauthorized disclosure or compliance violations.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The description 'AI intelligent ai-intelligent-knowledge-base' is overly generic and does not clearly define the skill's purpose, scope, or safe invocation boundaries. In an agent ecosystem, vague descriptions can cause the skill to be invoked in unintended contexts, increasing the risk of inappropriate data access, misleading routing, or accidental execution of capabilities beyond the user's intent.

VirusTotal

66/66 vendors flagged this skill as clean.