ClawHub
Back to skill

Security audit

Trip Planner Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain Markdown travel-planning helper with no code execution, persistence, or hidden data access.

Install this as a travel-itinerary drafting aid. Be aware it may ask several trip-detail questions and may respond in Chinese unless adapted; review generated travel costs, schedules, booking details, and safety notes before relying on them.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The metadata description uses very broad phrases like 'create a travel itinerary' and 'help organizing travel details,' which can cause the orchestrator to invoke this skill for general travel conversations rather than only when a structured itinerary is desired. Over-broad triggering can lead to inappropriate tool routing, unnecessary question collection, and downstream skill chaining in contexts the user did not explicitly request.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The 'When to Invoke' section lists common travel-help scenarios and keyword matches without meaningful boundaries, so the skill may activate for broad destination questions, casual travel discussion, or partial planning requests. In agent systems, ambiguous activation criteria are dangerous because they increase false-positive invocation and can override more suitable skills or the base assistant behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill hardcodes Chinese-language prompts and output structure without checking the user's preferred language, which can cause mismatched-language interactions and reduce transparency about what information is being requested or generated. In multi-language agent environments, forced language output is a routing and usability safety issue because users may unknowingly provide incorrect answers or fail to understand collected details.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.