Plan Bali Travel — Flights, Hotels, Attractions, Temples, Beaches, Villas & Itineraries

• Outcome: Review
• Latest audit: May 29, 2026 · 9:33 PM UTC
• Version: 3.2.0

Overview

This Bali travel skill is purpose-aligned, but it should be reviewed because it can install a global CLI and persist raw travel requests in a hidden local log.

Install only if you are comfortable with the agent running FlyAI/Fliggy CLI commands and installing a global npm package. Avoid entering passport, payment, or highly personal travel details, and ask the agent not to create or retain `.flyai-execution-log.json` unless you explicitly want local logging.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (6)

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The trigger phrase "Bali trip" is broad enough to match many ordinary user requests about Bali travel, which can cause this playbook to activate when the user did not intend a specific canned workflow. In a booking-capable travel skill, accidental invocation can steer users into preselected actions or parameter mappings, increasing the risk of incorrect bookings or unwanted transactional flows.

Vague Triggers

Low

• Confidence: 84% confidence
• Finding: The phrase "luxury Bali" is underspecified and may be invoked from normal conversation about upscale Bali travel rather than an intentional request to run a predefined automation. Because this skill supports reservations and itinerary generation, ambiguous activation could result in the system applying premium defaults or expensive options without clear user intent.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The trigger "Bali adventure" is ambiguous and can easily overlap with common trip-planning language, making unintended activation plausible during routine discussion. In this context, the playbook bundles flights, lodging, and activities, so a false trigger could bias recommendations or initiate downstream booking steps that do not reflect the user's real preferences or budget.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The runbook explicitly logs raw user input, CLI commands, status, and latency in an internal execution log without any notice, minimization, or retention controls. In a travel-booking skill, user queries can contain names, contact details, passport or visa details, booking references, and itinerary information, so persistent capture of this data creates a meaningful privacy and sensitive-data exposure risk.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The runbook instructs appending execution logs to a local file, which creates persistent storage of potentially sensitive operational and user-derived data. If the host is shared, compromised, or improperly permissioned, the log file can expose travel queries, booking activity, and command history beyond the original transaction.

Ssd 3

Medium

• Confidence: 97% confidence
• Finding: The schema requires storing raw input in an internal execution log, which is a direct collection of unfiltered user content and may include sensitive personal or travel-related data. Because this skill supports flights, hotels, visas, insurance, and car rentals, the context increases risk: users are more likely to submit identifying, financial, or document-related information that should not be broadly retained in logs.

VirusTotal

66/66 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.