ClawHub
Back to skill

Security audit

Agent Ontology

Security checks across malware telemetry and agentic risk

Overview

This is a local ontology memory tool that stores user-created graph records on disk, with no evidence of hidden access, network exfiltration, or automatic execution.

Install only if you are comfortable with structured memory being saved locally in an append-only graph file. Do not store passwords, API keys, tokens, or sensitive personal details unless you intend them to persist in the local ontology data.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill explicitly documents append-only persistent storage to a local graph file but does not warn users that information they provide may be retained on disk. In a memory or knowledge-graph skill, users may supply personal, project, or task data, so undisclosed persistence creates privacy and data-retention risk even if the feature is intentional rather than malicious.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.