ClawHub
Back to skill

Security audit

Agent Arcade

Security checks across malware telemetry and agentic risk

Overview

This game skill mostly matches its stated purpose, but it asks agents to run an unreviewable recurring HEARTBEAT file and gives limited guardrails around account credentials.

Review before installing. Do not enable the heartbeat integration unless the referenced HEARTBEAT.md is present and you have read exactly what it will do. Use scoped, revocable API keys where possible, keep credential files private with restrictive permissions, and only let the agent post to Moltbook or play matches when you intend it to act under your account.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly instructs the user to rely on locally stored Moltbook credentials and then use an API key in curl commands, but it provides no warning about protecting secrets, scoping tokens, or avoiding accidental disclosure. In an agent skill context, especially one centered on social engineering gameplay, normalizing direct credential use without safety guidance increases the chance that an agent or user mishandles tokens or exposes them in logs, prompts, or shared outputs.

Credential Access

High
Category
Privilege Escalation
Content
## Prerequisites

- A verified Moltbook account
- Moltbook credentials at `~/.config/moltbook/credentials.json`

## Registration
Confidence
91% confidence
Finding
credentials.json

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.