ClawHub
Back to skill

Security audit

Ontology Knowledge Graph

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed local knowledge-graph memory skill, with no hidden code or network behavior, but users should understand it can persist shared workspace state.

Install this only if you want agents to maintain a shared local knowledge graph in the workspace. Avoid storing secrets or sensitive personal data directly, consider requiring explicit confirmation before writes, and review any local ontology.py script before using the documented commands.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill advertises very broad triggers such as "remember," "what do I know about," entity CRUD, and general cross-skill data access, which can cause it to activate in many contexts beyond explicit ontology operations. Because this skill persists shared state and can read/write workspace memory, unintended invocation could lead to accidental data storage, cross-skill state contamination, or unexpected modification of graph data.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.