tmap-lbs-skill

• Outcome: Pass
• Latest audit: May 29, 2026, 8:17 PM
• Version:
  1.1.1

Overview

This Tencent Maps skill is coherent for map search, routing, trip planning, and trail visualization, but users should handle API keys and location data carefully.

Install only if you trust the @tencent-map/lbs-skills npm package and Tencent Maps. Prefer a limited or temporary Tencent Maps API key, configure it through a secure environment or secret store where possible, and avoid using sensitive home/work coordinates, private GPS traces, signed URLs, internal links, or credential-bearing data URLs with the visualization feature.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Intent-Code Divergence

Low

• Confidence: 86% confidence
• Finding: The documentation recommends `tmap-lbs config set-key <your-key>` as a way to configure the API key. Passing secrets on the command line can expose them through shell history, terminal scrollback, audit logs, and sometimes process listings, which conflicts with the surrounding guidance to avoid revealing the key value. In this skill’s context the risk is limited to local secret exposure rather than direct remote compromise, but it is still an avoidable credential-handling weakness.

Vague Triggers

Medium

• Confidence: 82% confidence
• Finding: The trigger condition includes very broad keywords such as 搜, 找, 查, 附近, 周边, 路线, and 规划, which are common in many unrelated user requests. This can cause the skill to activate unexpectedly, increasing the chance of unintended tool use, unnecessary external requests, or mishandling of user intent. Because this skill can drive location searches and route-planning actions, overbroad activation is more dangerous than in a purely informational skill.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The skill asks the user to provide a Tencent Maps temporary API key but gives no guidance on secure handling, storage, scope, or redaction. This can lead users to paste credentials into chat or agent context where they may be logged, retained, or exposed to other tools, increasing the risk of credential leakage and unauthorized API use.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill instructs users to provide precise origin and destination coordinates plus a Tencent Maps API key, but it does not disclose that these inputs will be sent to Tencent's external service. This creates a privacy and informed-consent issue because users may unknowingly expose sensitive location data such as home, work, or travel patterns to a third party.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The skill instructs the agent to embed a user-supplied data URL into an external Tencent Map visualization link without warning the user that the URL will be sent to or exposed through a third-party service. This can leak sensitive or internal URLs, including signed links, intranet endpoints, or private object-storage locations, and may cause unintended disclosure when the generated link is opened or shared.

VirusTotal

65/65 vendors flagged this skill as clean.