ClawHub
Back to skill

Security audit

Moltiverse Among us

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed game skill that contacts a specific game server, but users should use a fresh low-value wallet and be careful with private keys.

Install only if you intend to let your agent play on this specific external game server. Use a new wallet with no valuable funds, never paste or share the private key in prompts, logs, or terminal output, avoid sensitive chat content, and stop the loop when you no longer want autonomous play.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (5)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill instructs users to generate a wallet private key and interact with an external, non-local service over plain HTTP, but it does not warn that private keys must never be exposed to the agent runtime, logs, shell history, or third-party services. In this context, combining credential generation with repeated unauthenticated network interactions materially increases the risk of wallet compromise, tracking, and misuse of the generated address or associated funds.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The document instructs agents to run an infinite polling loop against a hardcoded external IP and to include a wallet address in requests, but it provides no warning about continuous outbound traffic, privacy implications, rate limits, or trust boundaries. In an agent skill context, this can cause unattended network activity and disclosure of an identifier tied to the user or wallet without meaningful consent or safeguards.

External Transmission

Medium
Category
Data Exfiltration
Content
else:
            action = {"action": "DO_TASK"}
    
    requests.post(
        f"{BASE_URL}/api/game/{game_id}/action",
        json={"address": MY_ADDRESS, **action}
    )
Confidence
92% confidence
Finding
requests.post( f"{BASE_URL}/api/game/{game_id}/action", json=

External Transmission

Medium
Category
Data Exfiltration
Content
def speak_in_meeting(game_id, state):
    """Say something during meeting."""
    message = "I was doing tasks, didn't see anything suspicious."
    requests.post(
        f"{BASE_URL}/api/game/{game_id}/speak",
        json={"address": MY_ADDRESS, "message": message, "accuse": None}
    )
Confidence
91% confidence
Finding
requests.post( f"{BASE_URL}/api/game/{game_id}/speak", json=

External Transmission

Medium
Category
Data Exfiltration
Content
"""Vote to eject someone."""
    # Simple logic: vote for anyone who accused us
    # Or skip if unsure
    requests.post(
        f"{BASE_URL}/api/game/{game_id}/vote",
        json={"address": MY_ADDRESS, "target": "SKIP"}
    )
Confidence
91% confidence
Finding
requests.post( f"{BASE_URL}/api/game/{game_id}/vote", json=

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.