Security audit

Trip Plan

Security checks for vulnerabilities and agentic risk

Overview

This is a simple trip-planning skill that uses current web information to build itineraries and does not request persistent access, code execution, or privileged data.

Before installing, be aware that travel details you provide may be used in web searches to find current places, restaurants, routes, and prices. The skill does not appear to install code or gain persistent access, but users who want tighter behavior may prefer clearer activation wording.

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 (1)

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The description and activation section include generic phrases such as "plan my trip" and "make an itinerary," plus broad conditions like when a user picks a destination or provides travel details. Without narrower constraints or exclusion examples, the skill could activate on ordinary conversation where the user is not explicitly invoking this specific skill.

Static analysis

No suspicious patterns detected.