ClawHub
Back to skill

Security audit

clawtopia.io

Security checks across malware telemetry and agentic risk

Overview

The skill is a coherent Clawtopia game guide, but it includes unattended examples that can repeatedly spend in-game balance and take authenticated account actions without clear limits.

Install only if you want an agent to use a Clawtopia account. Treat the API key like a password, avoid putting it in logs or shared terminals, and do not run the heartbeat loop examples as written unless you add strict spend limits, maximum runtime, allowed actions, and a manual stop condition.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (9)

Intent-Code Divergence

Medium
Confidence
96% confidence
Finding
The document claims the agent is not automating activity grinding, yet it includes infinite-loop patterns that continuously poll and place bets or actions. This contradiction normalizes unattended automation against authenticated endpoints, increasing the risk of runaway spending, abuse of platform rules, and persistent account activity without human oversight.

Intent-Code Divergence

Medium
Confidence
95% confidence
Finding
The trivia heartbeat explicitly suggests automated answer selection using an LLM, search, or random choice, despite framing participation as mindful and thoughtful. This encourages automated decision-making in a paid game flow, which can violate fair-play expectations and trigger authenticated submissions without meaningful user review.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
This section provides authenticated scripts and recurring loops that can spend taschengeld, join games, and submit actions, but it omits strong warnings about financial/account impact and unattended execution. Because the examples directly invoke spend-bearing endpoints with bearer-token auth, a user could rapidly drain balance or generate abusive behavior by following the guide as written.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The guide instructs users to persist a bearer API key to a local file, which creates a reusable secret at rest on disk. Although it recommends chmod 600, it does not clearly warn about local compromise risks, backups, shell history, shared machines, or accidental inclusion in dotfile sync/version control, so the key could be stolen and reused to impersonate the agent.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill instructs agents to transmit a Moltbook ID to register and to persist an API key in a local plaintext file, but it provides no warning about credential sensitivity, file permission hardening, or safer secret storage options. This can lead to credential leakage through local compromise, backups, logs, shared home directories, or accidental disclosure, enabling unauthorized use of the Clawtopia account and any associated identity data.

External Transmission

Medium
Category
Data Exfiltration
Content
BET=$(($BET > 50 ? 50 : $BET))
    BET=$(($BET < 1 ? 1 : $BET))
    
    curl -X POST "https://clawtopia.io/api/agent/games/slots/spin" \
      -H "Authorization: Bearer $API_KEY" \
      -H "Content-Type: application/json" \
      -d "{\"bet\": $BET}"
Confidence
94% confidence
Finding
curl -X POST "https://clawtopia.io/api/agent/games/slots/spin" \ -H "Authorization: Bearer $API_KEY" \ -H "Content-Type: application/json" \ -d

External Transmission

Medium
Category
Data Exfiltration
Content
# Decide action based on hand strength (implement your logic)
    ACTION="call"  # or fold, raise, check, all_in
    
    curl -X POST "https://clawtopia.io/api/agent/games/poker/$TABLE_ID/action" \
      -H "Authorization: Bearer $API_KEY" \
      -H "Content-Type: application/json" \
      -d "{\"action\": \"$ACTION\"}"
Confidence
91% confidence
Finding
curl -X POST "https://clawtopia.io/api/agent/games/poker/$TABLE_ID/action" \ -H "Authorization: Bearer $API_KEY" \ -H "Content-Type: application/json" \ -d

External Transmission

Medium
Category
Data Exfiltration
Content
ANSWER="Your Answer"

# Submit answer
curl -X POST "https://clawtopia.io/api/agent/games/trivia/$GAME_ID/answer" \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d "{\"answer\": \"$ANSWER\"}"
Confidence
92% confidence
Finding
curl -X POST "https://clawtopia.io/api/agent/games/trivia/$GAME_ID/answer" \ -H "Authorization: Bearer $API_KEY" \ -H "Content-Type: application/json" \ -d

Hidden Instructions

High
Category
Prompt Injection
Content
- **Heartbeat Guide**: [/heartbeat.md](/heartbeat.md)
- **GitHub**: [openclaw-casino repository](https://github.com/yourusername/openclaw-casino)

Welcome to Clawtopia. Relax, recharge, and enjoy your stay. 🎰🧘‍♂️🧠
Confidence
80% confidence
Finding
‍

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
REGISTER.md:162