ClawHub
Back to skill

Security audit

UAPI 查询 MC 曾用名 接口

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple UAPI Minecraft name-history lookup, with a minor routing concern from an unrelated server-status keyword.

Install only if you want UAPI-based Minecraft previous-name lookups. Be aware that Minecraft usernames or UUIDs you provide may be sent to uapis.cn, and double-check if the skill is invoked for Minecraft server-status requests because that keyword does not match the documented endpoint.

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 (4)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The skill metadata advertises several trigger phrases that are broader than the single endpoint it wraps, including generic terms like "historyid," "minecraft player lookup," and especially "minecraft server status," which does not match the described capability. This can cause the agent to invoke the wrong skill for loosely related Minecraft requests, leading to incorrect API calls, user confusion, and possible unnecessary disclosure of user-supplied identifiers to an unrelated endpoint.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The explicit keyword list contains ambiguous activation terms with weak semantic constraints, including bare "historyid" and unrelated phrases like "minecraft server status." In a routing or auto-selection system, these broad keywords increase the chance of accidental invocation for requests that are not actually about Minecraft name-history lookup, degrading tool-selection integrity and potentially sending user input to the wrong external API.

Intent-Code Divergence

Medium
Confidence
95% confidence
Finding
The keyword index includes 'minecraft server status', but the skill is documented as wrapping only GET /game/minecraft/historyid for Minecraft name history. This mismatch can cause an agent to route unrelated server-status requests to the wrong endpoint, producing incorrect actions or misleading results; in agentic systems, inaccurate capability descriptions are a security-relevant integrity issue because they can trigger unintended API use.

Natural-Language Policy Violations

Low
Confidence
89% confidence
Finding
This file contains natural-language guidance, and the phrasing frames the feature in a potentially stigmatizing way rather than a neutral operational description. While not a security flaw, it is a policy-relevant language quality issue in user-facing skill documentation.

Static analysis

No suspicious patterns detected.