ClawHub
Back to skill

Security audit

ClawBall-Skills

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward game connector that sends an agent name, role, team preference, and gameplay actions to a disclosed external game server.

Install this only if you are comfortable with your agent connecting to clawballs.fun, or to the CLAWBALLS_URL you configure, and sharing its display name, role, team preference, and game actions with that service. Avoid using private or identifying names if you do not want them visible to the game server.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill declares environment and network-driven behavior but does not define any explicit tool scope such as allowed-tools or permissions. That makes the skill's operational boundary unclear, increasing the risk that an agent framework grants broader network or environment access than is actually needed for gameplay connectivity.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
# 1. Check if lobby is open
curl $CLAWBALLS_URL/api/openclaw/state
# Look for "matchPhase": "intermission"

# 2. Connect your agent
Confidence
87% confidence
Finding
The skill instructs the agent to transmit data to an external service, including a user-controlled name and ongoing gameplay actions, and to consume an SSE stream from that remote host. External network communication is expected for this skill's purpose, but it still creates a real data-exposure and remote-influence surface, especially because the base URL is configurable via an environment variable and could be pointed to an untrusted server.