Back to skill

Security audit

Travel Planner Mastery

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown travel-planning guide with broad but disclosed travel advice and no executable behavior.

Reasonable to install if you want a general travel-planning template. Avoid entering unnecessary medical, identity, or budget details, and verify visa, health, safety, and booking information against official sources before acting.

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
  • 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 (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The skill description is very broad ('Complete travel planning system' and 'Use when planning any trip'), which increases the chance of unintended invocation for many generic travel-related requests. Over-broad routing can expose user context to the wrong skill, produce irrelevant outputs, and crowd out more specialized skills, especially in agentic systems that auto-select tools from natural language.

Vague Triggers

Medium
Confidence
97% confidence
Finding
The natural-language command 'Review my itinerary' is a vague, common phrase that could appear in ordinary conversation and trigger the skill unintentionally. In an auto-invocation environment, this can cause overreach into user workflows, accidental context consumption, or incorrect tool selection when the user did not explicitly request this skill.