Back to skill

Security audit

Amap Traffic

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it claims: it reads an Amap API key and sends route/location queries to Amap for traffic and driving-route results.

Install only if you are comfortable providing an Amap API key and sending origin/destination addresses or coordinates to Amap. Protect the OpenClaw config file and avoid using this with highly sensitive precise locations unless that third-party sharing is acceptable.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Lp3

Medium
Category
MCP Least Privilege
Confidence
96% confidence
Finding
The skill advertises capabilities that imply environment access, local file reads, and outbound network use, but it does not declare an explicit tool scope such as permissions or allowed-tools. This weakens least-privilege controls and makes it harder for users or the platform to understand and constrain what the skill can access, especially since it reads a local config file containing secrets and sends requests to an external API.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The documentation states that the skill dynamically reads AMAP_KEY from a local config file and sends route-planning requests containing origin and destination data to the Amap API, but it does not warn about secret handling or third-party transmission of sensitive location data. This can lead users to expose credentials and personal travel information without informed consent or proper operational safeguards.

Context-Inappropriate Capability

Medium
Confidence
86% confidence
Finding
The manifest describes a map traffic and route-planning skill, but this code also probes user-specific local filesystem paths and falls back to environment variables to obtain credentials. While using an API key is expected, directly reading host config files and environment state is a broader capability than the stated end-user purpose and is not mentioned in the manifest description.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The script geocodes the provided origin and destination by sending address data to Amap over HTTP requests. Although the network behavior is visible in code, there is no user-facing disclosure that entered location data will be transmitted to a third-party service, which is a privacy-relevant operation.

Natural-Language Policy Violations

Low
Confidence
81% confidence
Finding
Policy-violation checks apply to all file types, including markdown. The natural-language content and usage instructions are presented only in Chinese, which can impose a language constraint on users without an explicit opt-in or justification.

Missing User Warnings

Low
Confidence
80% confidence
Finding
The code accesses AMAP_KEY from user config files and falls back to an environment variable, which is access to sensitive credentials. While this is likely necessary for the skill, the file provides no explicit disclosure beyond usage guidance that credentials are being read from local config or environment sources.

Static analysis

No suspicious patterns detected.