ClawHub
Back to skill

Security audit

UAPI Adcode 国内外行政区域查询 接口

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed wrapper for a public UAPI administrative district lookup endpoint, with no executable code or persistence.

Installers should know this skill may send administrative-region search terms, adcodes, or coordinates to UAPI when invoked. Use it for explicit administrative district lookup tasks, and be mindful that the broad 'district' trigger could select it when another district-related task was intended.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger keywords include very generic English terms such as "district" and "district lookup", which can match many unrelated user requests and cause this skill to be selected when a more appropriate tool should handle the task. In an agentic system, unintended invocation can lead to wrong API calls, disclosure of user query details to an external service, or confused workflow execution.

Natural-Language Policy Violations

Low
Confidence
83% confidence
Finding
The description prominently presents the skill in Chinese and names the interface in Chinese, without stating that responses or operation can adapt to the user's preferred language. This can conflict with a language/locale policy if the organization expects user language choice or opt-in rather than an implicit default.

Natural-Language Policy Violations

Low
Confidence
85% confidence
Finding
The file presents invocation keywords in both Chinese and English but does not state that language choice is optional or user-driven. This can be interpreted as imposing preset locale expectations rather than explicitly honoring the user's preferred language.

Static analysis

No suspicious patterns detected.