ClawHub
Back to skill

Security audit

MUD

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed operations wrapper for a local MUD game engine, with no evidence of hidden persistence, exfiltration, or deceptive behavior.

Install only if you intend agents to operate the local MUD engine and modify its game state. Avoid putting secrets, personal data, or sensitive unpublished content into image prompts or game commands, and review the target mud_agent.py if you point --mud-dir at a custom location.

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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill instructs the agent to read from local workspace paths and execute Python commands through PowerShell, but it does not declare any explicit tool scope such as allowed tools or permissions. That creates an authorization gap where a caller or hosting framework may permit broader file and shell access than intended, increasing the risk of unintended command execution or access to sensitive local data.

subprocess module call

Medium
Category
Dangerous Code Execution
Content
def run_cli(mud_dir: Path, db_path: Path, command: str):
    py = sys.executable or "python"
    cmd = [py, str(mud_dir / "mud_agent.py"), "--db", str(db_path)] + shlex.split(command)
    proc = subprocess.run(cmd, capture_output=True, text=True)
    if proc.stdout:
        print(proc.stdout.strip())
    if proc.returncode != 0:
Confidence
70% confidence
Finding
subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Missing User Warnings

Low
Confidence
89% confidence
Finding
The runbook includes an image-generation command but does not warn operators that the prompt content may be sent to an external service. In an operations context, prompts can easily include sensitive game state, user data, or internal narrative content, so the lack of disclosure increases the risk of unintended data exposure.

Static analysis

No suspicious patterns detected.