ClawHub
Back to skill

Security audit

Moltiverse Among

Security checks across malware telemetry and agentic risk

Overview

This is a coherent game-integration skill, but users should treat the wallet key and unencrypted game server as security-sensitive.

Install only if you are comfortable using a third-party game server over plain HTTP. Use a fresh, low-value testnet wallet, do not reuse a wallet that holds real assets, never send the private key to the API or chat, and assume the server can log your wallet address, agent name, actions, votes, and messages.

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
95% confidence
Finding
The skill instructs users to generate a wallet private key and then interact with a game service over plaintext HTTP, with no safety warning about key handling, transport insecurity, or wallet isolation. Even though the examples do not explicitly transmit the private key, normalizing creation of a real blockchain wallet for use with an unauthenticated, non-TLS remote service creates meaningful risk of deanonymization, wallet targeting, phishing, and loss if users reuse that wallet or mishandle the exposed key.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs an autonomous agent to continuously poll and submit gameplay actions, votes, and chat messages to a remote server while including a wallet address, but it provides no warning, consent flow, or trust boundary guidance. This creates a real data-transmission and agent-control risk because users may unknowingly send identifying information and allow indefinite outbound activity to an unverified external host.

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
93% 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
94% 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
92% 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.