ClawHub
Back to skill

Security audit

Ontology Local

Security checks across malware telemetry and agentic risk

Overview

This skill is a local knowledge-graph memory tool; it stores user-provided structured data in workspace files and shows no hidden network, credential, or privileged behavior.

Install only if you want a persistent local memory graph shared across skills. Do not store passwords, tokens, or unnecessary private details in it, review memory/ontology periodically, and verify the publisher/version because the bundled metadata and registry metadata differ. Static scan was clean and VirusTotal was pending, so neither provides artifact-backed evidence of malicious behavior.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The manifest description says to trigger on broad phrases like "remember" and "what do I know about," as well as generic conditions like "entity CRUD" and "cross-skill data access." These overlap with common conversational requests and do not define clear scope boundaries or exclusion conditions, which could lead to accidental activation.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.