ClawHub
Back to skill

Security audit

黄金价格查询 - Gold Price Inquiry

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed gold-price lookup wrapper around JisuAPI, with no hidden persistence, local data collection, destructive behavior, or unrelated authority.

Install only if you are comfortable configuring a JisuAPI key and having gold-price lookup parameters sent to JisuAPI. Treat returned prices as reference market data, not investment advice.

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 (6)

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.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill declares it requires an environment variable and implicitly depends on outbound network access, but it does not explicitly scope or constrain those capabilities with a permissions or allowed-tools declaration. In an agent ecosystem, missing tool scoping weakens least-privilege enforcement and can let a skill execute with broader access than intended, increasing the blast radius if the script is modified, compromised, or invoked in an unexpected context.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The trigger rules include broad phrases such as trend and future-outlook wording that can match general gold-market discussion, not just concrete price lookup requests. Overbroad routing can cause the agent to invoke this networked skill unnecessarily, expose API-backed data retrieval in unrelated conversations, and increase the chance of misleading responses when the skill is used outside its narrow intended purpose.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

The code is designed to transmit data to an external API endpoint, which creates a real trust-boundary crossing. In this skill's context, the transmission is functionally necessary, but it still exposes request metadata and authentication material to a third party and creates dependency on the security/privacy posture of api.jisuapi.com.

Content

Scanner excerpt · gold.py (reported line 14)May include surrounding context.

python
import requests


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


def _call_gold_api(path: str, appkey: str, params: dict = None):

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The module docstring and several command descriptions use Chinese-language text, which imposes a language choice in user-visible natural language. The policy allows fixed locale behavior only when the constraint is justified or when the user is offered a language choice, neither of which is stated here.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill sends request parameters and the JISU API key to a third-party service without any explicit user-facing disclosure or consent flow. While outbound network access is expected for a price-lookup skill, transmitting user-supplied query parameters off-system can create privacy and transparency issues, especially in agent environments where users may not realize an external provider is involved.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.