Back to skill

Security audit

dive trip planner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward dive-trip planning prompt that uses travel details to query flyai, with privacy disclosure improvements recommended but no malicious behavior found.

Before installing, understand that the skill will ask for trip details such as dates, budget, party size, lodging needs, dive certification, and travel preferences, then use flyai to look up options and booking links. Avoid sharing information you do not want used for travel search, and prefer an updated version that gives a clear notice before third-party queries.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger examples are broad enough to match generic travel-assistance requests such as finding shops or planning trips, which can cause the skill to activate outside a narrowly scoped diving context. That increases the chance of unnecessary collection and transmission of itinerary, budget, and traveler details to flyai when the user may not have intended to invoke this specific skill.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill collects detailed personal and trip data including origin city, exact dates, party composition, budget, and preferences, then instructs the agent to query a third-party service, but it does not warn the user or obtain clear consent before sharing that data. This creates a privacy and data-handling risk because users may disclose sensitive travel information without understanding that it will be processed externally.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill description and all example interactions are written as mandatory Chinese-language behavior, with no indication that users may choose another language. This can violate language or locale policy when a skill implicitly forces one language without opt-in or documented regional justification.

Content

No source excerpt is available for this finding.