ClawHub
Back to skill

Security audit

oasis

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently teaches an agent how to use a local 3D world-building MCP integration, with no evidence of hidden execution, exfiltration, persistence, or deceptive behavior.

Install only if you intend to let an agent edit your local Oasis worlds. Before asking it to remove objects, clear worlds, load another world, or delete conjured assets, give explicit instructions about confirmation and backups or snapshots if the world contains work you care about.

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
  • 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
88% confidence
Finding
The skill advertises powerful mutation tools such as object placement, removal, world loading, and clearing, but it does not prominently warn the agent to obtain explicit user confirmation before destructive or potentially irreversible actions. In a local-first shared 3D world, an agent could misinterpret an ambiguous prompt and modify or erase user-created content, causing unintended loss or disruption.

Static analysis

No suspicious patterns detected.