Knowledge Management System

Security checks across malware telemetry and agentic risk

Overview

This appears to be a documentation-focused knowledge management skill, with privacy cautions around credentials and internal sources but no evidence of hidden or harmful behavior.

Install if you want an agent to help structure organizational knowledge and documentation. Do not paste raw credentials or secrets into generated docs, and only let it use Slack, meeting notes, or internal documents that are approved for the intended audience.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The interview guide explicitly asks for 'tools, credentials, or access' needed to perform a process, but provides no instruction to avoid recording secrets or to use secure secret-management references instead. In a knowledge-management skill, users may copy passwords, tokens, or privileged access details into durable documentation, creating unnecessary exposure and long-lived credential leakage risk.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The chatbot design includes Slack-sourced answers and meeting notes as searchable knowledge sources without any privacy, classification, or redaction controls. Those sources commonly contain credentials, customer data, HR discussions, incident details, or legal-sensitive material, so indexing and surfacing them via chat can broaden access and leak sensitive information to unintended audiences.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal