ClawHub
Back to skill

Security audit

Trip Planner CN

Security checks for vulnerabilities and agentic risk

Overview

This travel-planning skill is purpose-aligned and contains no executable code, persistence, or hidden privileged behavior, though users should understand it may send itinerary details to travel and map services.

Install only if you are comfortable sharing trip locations, dates, timing constraints, and related itinerary details with the travel and map services used by the skill. Avoid providing unnecessary personal details, and configure the Baidu Maps API key only if you want driving-time lookups.

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
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger phrases are very broad and map to common travel-related queries, which can cause the skill to activate in situations where the user did not clearly consent to this specific workflow. In this skill's context, unintended activation is more concerning because the skill is designed to query external travel services and potentially process detailed itinerary and location information, increasing the chance of unnecessary data exposure or user confusion.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill does not clearly warn users that their itinerary details, locations, and timing constraints may be sent to external services such as Ctrip and Baidu Map APIs. In this context, the omission is meaningful because travel plans can reveal sensitive behavioral and location data, and users may not expect third-party processing without explicit notice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.