ClawHub
Back to skill

Security audit

Tartarian WEBMCP Prototype

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed operator guide for controlling a Tartarian.ai game session and does not show hidden code, persistence, exfiltration, or unrelated authority.

Install this only if you want an agent to operate your current Tartarian.ai browser session. It may move your character, interact with resources or objects, and activate prepared commands in a persistent game world, so give clear instructions before state-changing actions and do not paste session cookies, tokens, or other private authentication material into chat.

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
Confidence
84% confidence
Finding
The skill description is very broad and can cause the agent to be invoked for many loosely related tasks involving live world operation. Because the skill acts through an authenticated human session, unclear trigger boundaries increase the chance of unintended actions in a persistent environment, including movement, interaction, or command activation when a narrower skill would have been more appropriate.

Static analysis

No suspicious patterns detected.