Back to skill

Security audit

travel planner amap

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Chinese travel-planning skill that uses a disclosed AMAP API key and travel details to build itineraries, with privacy considerations users should understand.

Install only if you are comfortable sharing trip details such as origin, destination, dates, group composition, budget, and preferences with AMAP and, for weather, a web search provider. Use a restricted AMAP Web Service key as instructed, avoid storing it permanently in shell startup files, and remove or skip WebSearch weather lookup if you want to minimize third-party exposure.

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
  • 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
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly gathers sensitive itinerary attributes including origin, destination, dates, group composition, and relationship, then transmits parts of that data to external APIs and web search without an explicit privacy warning. This creates a real privacy and consent issue because travel plans can reveal location history, future whereabouts, and personal associations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

Core instructions, trigger phrases, prompts, and output template are all specified in Chinese, and the skill directs the interaction in that language by default. There is no indication that users may choose another language or that the Chinese-only behavior is a justified region-specific requirement.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are broad enough to match ordinary travel-related requests, which can cause the skill to activate when the user did not specifically intend to invoke this external-data workflow. Because the skill collects personal itinerary information and calls outside services, overbroad invocation increases the chance of unintended data sharing and surprising behavior.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill expands its data-access surface by instructing use of WebSearch for weather, even though the declared scope is an AMAP REST API-based planner. This sends user itinerary details such as destination and travel dates to an additional external service without clear necessity, increasing privacy exposure and making behavior less predictable to users and reviewers.

Content

No source excerpt is available for this finding.