Back to skill

Security audit

Map Route Reader

Security checks for vulnerabilities and agentic risk

Overview

This skill is a route-reading helper for Amap/Baidu that has a real privacy consideration around Browser Relay but no hidden code, install behavior, persistence, or unrelated data access.

Install this only if you are comfortable sharing route queries and map results with the agent. If Browser Relay is used, open a dedicated Amap or Baidu route tab and select only that exact tab, since visible route details may include sensitive locations.

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
  • 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 (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description is entirely written in Chinese, including all headings and usage descriptions, with no indication that users may choose another language. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly documented and justified.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly instructs the agent to switch to the user's live browser tab via Browser Relay to read route results, but it does not require a clear user consent flow or a privacy warning about exposure of visible tab contents. Accessing a live user tab can reveal unrelated sensitive data in the page, browser context, or adjacent UI state, so the omission creates a real privacy and data-exposure risk.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The description defines activation through broad examples like asking how to get from A to B, which can match many ordinary travel-related queries without clear boundaries. This can cause the skill to trigger when not explicitly intended, increasing the chance of over-collection of location context or unintended routing guidance being presented as authoritative.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill description is written only in Chinese and implies Chinese-language operation without stating whether language or locale is optional. This can lead to mismatched execution for users in other languages or regions, causing misunderstood instructions or unsafe navigation advice if route details are rendered in an unusable language.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.