ClawHub
Back to skill

Security audit

UAPI 查询 MC 玩家 接口

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Minecraft player lookup skill with some overly broad routing keywords, but no evidence of hidden code, persistence, local data access, or destructive behavior.

Installers should know this skill may be selected too broadly because of keywords like userinfo, minecraft server status, and minecraft name history. It should only be used for Minecraft player username lookups, and ambiguous requests should be confirmed before sending a username to the UAPI service.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger list includes the generic term "userinfo," which is far broader than the documented single endpoint for Minecraft player lookup. This can cause the agent to invoke this skill for unrelated requests involving personal or account information, leading to wrong-tool selection, unintended external API calls, and possible disclosure of user-supplied data to an unrelated third-party endpoint.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The keyword list mixes endpoint-specific phrases with broader or mismatched triggers such as "minecraft server status" and "minecraft name history," which may correspond to different functionality than `/game/minecraft/userinfo`. This increases the chance of semantic overreach where the orchestrator routes unrelated tasks to this skill, producing incorrect behavior or sending unnecessary user data to the wrong API.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill enables implicit invocation, but the trigger description is broad and ambiguous, covering generic terms like "userinfo" and related Minecraft queries. This can cause the agent to invoke the skill in situations the user did not clearly intend, leading to unnecessary external API calls, possible disclosure of user-supplied identifiers to a third-party service, and reduced user control over tool use.

Description-Behavior Mismatch

Medium
Confidence
97% confidence
Finding
The document states this skill only wraps `GET /game/minecraft/userinfo`, but the keyword index also routes `minecraft server status` and `minecraft name history` to it, which are different tasks. This mismatch can cause incorrect tool selection, sending the wrong request for a user’s intent and potentially exposing unrelated account data or causing downstream agents to act on false assumptions about the API capability.

Natural-Language Policy Violations

Low
Confidence
79% confidence
Finding
The description prominently frames the skill in Chinese and uses Chinese task naming, while also embedding English trigger phrases, but it does not state that output language should follow the user's preference. This can create an implicit locale bias without opt-in or documented justification.

Natural-Language Policy Violations

Low
Confidence
85% confidence
Finding
The file presents keyword and invocation examples in both Chinese and English, but does not state whether the skill should adapt to the user's preferred language or ask for a language choice. Under the policy rule, forcing or implying a locale/language behavior without opt-in can be a natural-language policy concern.

Static analysis

No suspicious patterns detected.