Back to skill

Security audit

open-map

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says: it opens a local map app for a user-provided destination, with no hidden scripts or persistence found.

Install only if you want an agent to open your local map application on explicit request. Destination text or coordinates may be handed to Apple Maps or another registered URL handler, so avoid sending sensitive locations unless that is intended; the publisher should ideally clarify trigger rules and encode destination parameters safely.

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

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

Natural-language content in the description, usage, and notes is exclusively Chinese, which can impose a language constraint on users without opt-in. The policy allows locale restrictions when they are explicitly documented and justified, but no such justification or alternative language option is provided here.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The skill launches a local GUI application and passes user-provided destination data to the system URL handler via the open command, but it does not explicitly warn users that external local application execution will occur. While the action is expected for a map skill, lack of disclosure can lead to unexpected app launches or unintended sharing of destination data with the OS map handler or another registered handler.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

This markdown file describes invocation using natural-language phrases like '打开地图 前往 北京 天安门' and '打开地图 坐标 ...', but it does not specify whether only these exact forms trigger the skill or what similar phrases should not trigger it. Without explicit scope or negative examples, the activation conditions may be interpreted too broadly and cause unintended invocation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.