ClawHub

Ontology

Security checks across malware telemetry and agentic risk

Overview

The skill appears to provide local shared memory, but its broad activation and persistent cross-skill storage need review before installation.

Install only if you want a persistent local memory layer shared across skills. Review what it stores under memory/ontology, avoid saving secrets or sensitive personal data, and prefer explicit user-directed write actions with a clear way to inspect and delete stored entries.

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
95% confidence
Finding
The skill explicitly instructs the agent to create directories and write to local workspace files (`memory/ontology/graph.jsonl`, `memory/ontology/schema.yaml`) but does not declare permissions. This creates a mismatch between the skill's documented behavior and its security contract, making file mutation harder to audit and increasing the chance of unintended or unauthorized persistence.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger conditions are very broad, including phrases like "remember," entity CRUD, shared state, and cross-skill data access. This can cause the skill to activate for many ordinary requests and silently persist or link user data into long-lived storage, especially because the skill is designed as shared memory across skills.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal