ClawHub
Back to skill

Security audit

Ontology

Security checks across malware telemetry and agentic risk

Overview

This is a local knowledge-graph memory skill whose persistent file writes are expected and disclosed, but users should treat the stored graph as sensitive.

Install only if you want a persistent local memory graph shared across workflows. Avoid storing secrets or highly sensitive personal data, review `memory/ontology/graph.jsonl` periodically, and delete or purge the ontology files manually if you need complete removal of retained history.

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 (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill explicitly instructs the agent to create and modify local workspace files under memory/ontology, but it does not declare corresponding permissions. Undeclared write capability weakens governance and review because users or orchestrators may not realize the skill can persist or alter shared state, increasing the chance of unintended data modification or cross-skill state poisoning.

Vague Triggers

Medium
Confidence
78% confidence
Finding
The trigger guidance is broad enough to activate on generic phrases like 'remember' or broad cross-skill data access requests, which can cause the ontology skill to run in situations where persistent storage was not intended. In a memory-oriented skill that writes shared graph data, over-triggering raises the risk of silent persistence, accidental linking of unrelated entities, and contamination of shared state consumed by other skills.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger list contains broad, generic terms such as knowledge management and query-related phrases that can match many unrelated user requests, increasing the chance this skill activates when the user did not intend to use it. Because this skill exposes shared structured memory and cross-skill state access, unintended activation could lead to inappropriate reads, writes, or linking of entities across workflows.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.