ClawHub
Back to skill

Security audit

play_minecraft

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only skill gives clear instructions for controlling a local Minecraft Mindcraft bot API and does not show hidden installation, persistence, credential access, or data exfiltration.

Install this only if you intend to let an agent control a local Mindcraft/Minecraft bot. Use it first in a private or local world, confirm the API is bound as expected, and review actions before allowing automation in shared worlds.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill description uses broad activation cues such as 'external agent', 'REST 接口控制', '读取状态', '执行动作', and '批量任务编排', which overlap with many ordinary automation requests. This can cause the skill to trigger in contexts where the user did not intend Minecraft bot control, leading an external controller to issue state reads or in-game actions against a live bot.

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
The markdown examples and headings are presented entirely in Chinese, and there is no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking audience. This can violate a language/locale policy when the skill implicitly forces a specific language without user opt-in.

External Transmission

Medium
Category
Data Exfiltration
Content
return r.json()

def api_post(path: str, payload: dict):
    r = requests.post(BASE + path, json=payload, timeout=120)
    r.raise_for_status()
    return r.json()
Confidence
70% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Natural-Language Policy Violations

Medium
Confidence
92% confidence
Finding
The title and all operational guidance in this markdown file are presented only in Chinese, with no indication that users may choose another language or that the skill is intentionally restricted to a Chinese-speaking context. Under the policy, a forced language or locale without opt-in is a natural-language policy violation.

Static analysis

No suspicious patterns detected.