Back to skill

Security audit

Amap Walk Route

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Amap walking-route planner, but users should understand that entered locations are sent to Amap APIs.

Install only if you are comfortable sending the locations or addresses you provide to Amap for geocoding, place search, weather, walking-route calculation, and QR-code route generation. Prefer approximate starting points when privacy matters, and protect the AMAP_API_KEY like any other API credential.

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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description explains setup and API usage but does not give users a prominent, upfront warning that their location or address will be transmitted to Amap's external HTTP APIs for geocoding, search, weather, and route generation. Because location data is highly sensitive, this omission can prevent informed consent and lead to privacy-impacting disclosures.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill is activated by very broad natural-language prompts such as telling it where you are and how far you want to walk, without clear trigger boundaries or exclusions. This increases the chance of unintended invocation and accidental disclosure of sensitive location data to the route-planning workflow and downstream external APIs.

Content

No source excerpt is available for this finding.