ClawHub
Back to skill

Security audit

企业工商信息查询 - Enterprise Business Information Inquiry

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward company-information lookup that sends user-entered business identifiers and an API key to JisuAPI as part of its stated purpose.

Install only if you are comfortable sending company names, registry identifiers, and your JISU_API_KEY to JisuAPI. Avoid submitting confidential investigative targets or sensitive business identifiers unless your organization approves that provider and data flow.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (7)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill declares that it requires an environment variable and, by design, calls a remote API, but the manifest does not explicitly scope or declare those capabilities via permissions/allowed-tools. This weakens operator visibility and policy enforcement, making it easier for a skill to access secrets and perform network egress without clear approval boundaries.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill description does not warn that company names, credit numbers, registration numbers, and similar query terms are transmitted to a third-party provider. Users may unknowingly send sensitive business identifiers or investigative targets to an external service, creating privacy, confidentiality, and compliance risks.

External Transmission

Medium
Category
Data Exfiltration
Content
import requests


BASE_URL = "https://api.jisuapi.com/enterprise"


def _call_enterprise_api(path: str, appkey: str, params: dict):
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill sends company names, registration numbers, unified credit codes, and similar identifiers to a third-party service over the network without any built-in user disclosure, consent step, or minimization controls. Even though this is the intended function of the skill, it still creates a real privacy and data-governance risk because potentially sensitive business lookup inputs are shared with an external provider and may be logged or retained there.

Natural-Language Policy Violations

Low
Confidence
88% confidence
Finding
The activation and usage guidance is written as a Chinese-only instruction ('当用户说...使用本技能') and the rest of the skill documentation is entirely Chinese, with no opt-in or alternative locale guidance. Under the stated policy, forcing a specific language without user choice is a natural-language policy concern.

Natural-Language Policy Violations

Low
Confidence
81% confidence
Finding
Natural-language strings in the module docstring, function docstrings, usage examples, and error-context comments are predominantly Chinese, which can impose a language preference on users without opt-in. The file does not indicate that the skill is region-specific or provide an alternative language option.

Static analysis

No suspicious patterns detected.