ClawHub
Back to skill

Security audit

Baidu Map

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Baidu Maps command-line helper that sends user-provided map queries to Baidu and does not show hidden persistence, local file access, or deceptive behavior.

Install only if you are comfortable providing a Baidu Maps server-side AK and sending queried addresses, coordinates, route endpoints, and other call parameters to Baidu Maps APIs. Be careful with the generic call command because it can use additional Baidu endpoints and may consume API quota.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill describes executable CLI behavior that uses environment variables and outbound network access, but it does not declare any tool scope such as permissions or allowed-tools. This creates a trust and containment gap: an agent or reviewer cannot easily tell that the skill may access secrets from the environment and send user-supplied data to Baidu APIs.

Natural-Language Policy Violations

Medium
Confidence
90% confidence
Finding
The skill name, headings, operational guidance, and examples are primarily written in Chinese, and there is no statement that the skill supports multiple languages or that Chinese is required by a region-specific constraint. This creates a natural-language locale policy concern because the skill effectively imposes a language choice on users without opt-in.

Context-Inappropriate Capability

Medium
Confidence
93% confidence
Finding
The manifest describes this skill as a Baidu Maps Web API CLI for geocoding, POI, routing, coordinate conversion, and development guidance. The documented `call <path> k=v...` subcommand adds a general-purpose capability to invoke arbitrary API paths, which is broader than those named functions and is not obviously required to implement them.

Context-Inappropriate Capability

Medium
Confidence
96% confidence
Finding
The `call` branch accepts any user-supplied path and forwards arbitrary key/value parameters to `api()`, enabling access to any Baidu Maps Web API endpoint under the base domain. This is a materially broader capability than a CLI specifically for geocoding, POI, routing, and coordinate conversion.

Static analysis

No suspicious patterns detected.