ClawHub
Back to skill

Security audit

Ontology Knowledge Graph

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed local knowledge-graph memory skill, with broad memory triggers but no bundled executable code, install hooks, network behavior, or hidden credential collection.

Install this only if you want the agent to keep reusable structured memory in local files under memory/ontology. Avoid storing plaintext secrets or sensitive personal data unless you have reviewed the actual implementation that will read and write those files.

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 trigger guidance is broad enough to activate the ontology skill for generic memory, planning, linking, CRUD, and cross-skill state requests. In an agent system, over-broad routing can cause this skill to read or write shared structured memory when the user intended a narrower tool, creating unintended persistence, data mixing across skills, or unauthorized access to previously stored context.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.