Back to skill

Security audit

GEO & Address Conversion - 经纬度地址转换

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward geocoding skill that uses JisuAPI to convert addresses and coordinates, with privacy considerations because submitted locations and the API key are sent to that provider.

Install only if you are comfortable sending the addresses or coordinates you ask about to JisuAPI. Use a dedicated JisuAPI key with quotas or restrictions where possible, avoid sensitive home/work locations unless necessary, and rotate the key if you suspect request URLs were logged or exposed.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
geoconvert.py:35
Finding

API Credential and Location Data Exposed in URL Query Parameters

Content
View full analysis
Remediation
View remediation
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 (8)

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
90% confidence
Finding

The skill declares that it requires an environment variable and, by design, calls an external API, but it does not declare an explicit tool scope such as permissions or allowed-tools. That weakens governance and review because an agent may invoke networked code with access to secrets without clear user- or platform-visible boundaries.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The invocation guidance uses broad triggers like 'similar map coordinate questions,' which can cause overbroad activation and unintended transmission of user location data to the external service. In this skill's context, vague routing increases privacy risk because even ambiguous geography-related queries may be escalated to a third party unnecessarily.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill routes user-supplied addresses and coordinates to a third-party API service, but the description does not clearly disclose this data sharing. Users may provide sensitive location data assuming local processing, creating privacy and consent risks when precise home, work, or travel locations are transmitted externally.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
86% confidence
Finding

This constant defines an external endpoint used for coordinate-to-address lookups, meaning user location inputs are transmitted outside the local system. In a geo-conversion skill this is contextually expected, but it still increases risk because sensitive location data and API usage metadata are exposed to a third party.

Content

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

python
import requests


COORD2ADDR_URL = "https://api.jisuapi.com/geoconvert/coord2addr"
ADDR2COORD_URL = "https://api.jisuapi.com/geoconvert/addr2coord"

External Transmission

Medium
Category
Data Exfiltration
Confidence
86% confidence
Finding

This endpoint sends user-supplied address data to an external geocoding provider for conversion to coordinates. While necessary for the feature, the transmission of potentially sensitive address information to a third party is a genuine privacy and data-governance concern if not disclosed and controlled.

Content

Scanner excerpt · geoconvert.py (reported line 15)May include surrounding context.

python
COORD2ADDR_URL = "https://api.jisuapi.com/geoconvert/coord2addr"
ADDR2COORD_URL = "https://api.jisuapi.com/geoconvert/addr2coord"


def coord2addr(appkey: str, req: dict):

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill sends precise latitude/longitude supplied by the user to a third-party geocoding service, but the code contains no notice, consent flow, or minimization around that disclosure. Location data can be sensitive personal information, so silent transmission to an external provider creates a real privacy risk even if the code is otherwise functioning as intended.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill forwards user-provided address data to an external API without any user-facing disclosure in the implementation. Addresses may reveal home, work, or other sensitive locations, so undisclosed third-party transmission is a meaningful privacy issue in this skill's context.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.