LLM Wiki — Build a Compounding Knowledge Base with LLMs

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed local Markdown/Obsidian wiki assistant with a read-only audit script and expected wiki maintenance workflows.

Install this if you want an agent to maintain a local Knowledge wiki. Give it access only to the intended vault, review proposed bulk renames or reorganizations before applying them, and treat the audit script output as local file-path diagnostics rather than external reporting.

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
88% confidence
Finding
The skill description is extremely broad ('build, maintain, query, archive, and audit... continuously maintained by an LLM') and encourages invocation across many tasks without narrow triggers or boundaries. In practice, this can cause an agent to activate the skill in loosely related contexts and perform wide file inspection or modifications to a user's knowledge base when the user did not clearly request those actions.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal