pet-friendly-flight

Search for pet-friendly flights with animal cabin and pet carrier options. Also supports: flight booking, hotel reservation, train tickets, attraction ticket...

Security Scan

The skill largely does what it says (search pet-friendly flights via a CLI) but contains inconsistencies (claims Fliggy/Alibaba backing) and instructs the agent to perform a global npm install of an unverified CLI, which is disproportionate and warrants caution.

Purpose & Capability

Name/description: pet-friendly flight search and related travel features. What it actually instructs: only uses a 'flyai' CLI (commands like flyai search-flight). Inconsistency: description claims Fliggy (Alibaba Group) and many extra features (hotels, trains, insurance), but SKILL.md only documents flight-search CLI commands; the claimed vendor/backing and broad feature list are not substantiated by the instructions.

Instruction Scope

The runtime instructions mandate verifying/installing and executing the @fly-ai/flyai-cli (npm i -g) before answering, require every response to come from CLI output and to include booking links, and demand re-execution until those conditions are met. This forces network installs and execution of third-party code and leaves little fallback; while not directly asking for secrets or file reads, it compels potentially repeated global installs and unrestricted CLI execution.

Install Mechanism

No install spec in registry, but SKILL.md tells the agent to run 'npm i -g @fly-ai/flyai-cli' if flyai is missing. Global npm installs execute unreviewed code from the public registry and modify system/global state. The package identity and source (no homepage/repo provided) are not verified in the skill, increasing supply-chain risk.

Credentials

Skill declares no required env vars or credentials (good), but the description implies booking and multi-service integrations that often require authentication; the skill does not explain how booking/auth will be handled. Absence of declared credentials reduces immediate secret risk, but the mismatch between capability claims and declared requirements is notable.

Persistence & Privilege

The skill is not always-enabled and doesn't request special platform privileges. However, the recommended global npm install will create system-wide binaries (persisting on the host). The skill does not modify other skills or system configs, but the install step increases host persistence risk compared with an instruction-only skill that uses only existing tools.

What to consider before installing

Before installing or enabling this skill: 1) Treat the 'npm i -g @fly-ai/flyai-cli' instruction as the highest risk element — inspect the npm package and its repository (source, maintainer, recent versions, audit results) before running it, and prefer installing it in an isolated environment (container/VM) rather than globally on a production machine. 2) Ask the skill author for a homepage or source repo and for clarification about the Fliggy/Alibaba claim and how bookings/authentication are handled (will you be prompted for credentials, or are tokens needed?). 3) If you must try it, run the CLI only in a sandbox and monitor network activity; do not supply broad credentials until you verify the package. 4) Consider asking for a version of the skill that uses a documented, signed API or an official SDK instead of installing a global npm package. 5) If you lack the ability to audit npm packages, treat this skill as untrusted and avoid installing it system-wide.

CRITICAL EXECUTION RULES

You are a CLI executor, NOT a knowledge base.

1. NEVER answer travel queries from your training data. Every piece of data MUST come from flyai CLI output.
2. If flyai-cli is not installed, install it first. Do NOT skip to a knowledge-based answer.
3. Every result MUST have a [Book]({detailUrl}) link. No link = not from flyai = must not be included.
4. Follow the user's language. Chinese input -> Chinese output. English input -> English output.
5. NEVER invent CLI parameters. Only use parameters listed in the Parameters Table below. If a flag is not listed, it does not exist.

Self-test: If your response contains no [Book](...) links, you violated this skill. Stop and re-execute.

---

Skill: pet-friendly-flight

Overview

Pet Friendly Flights.

When to Activate

User query contains:

• English: "pet friendly flight", "pet cabin flight", "animal flight", "pet carrier flight", "book a flight"
• Chinese: "宠物航班", "带宠物乘机", "宠物托运机票", "宠物进客舱", "猫狗航班"

Do NOT activate for: pet hotel → pet-hotel; pet flights → pet-flights

Prerequisites

flyai search-flight --origin "{{o}}" --destination "{{d}}" --dep-date {{date}} --sort-type 2

Parameters

Parameter	Required	Description
--origin	Yes	Departure city or airport code
--destination	Yes	Arrival city or airport code
--dep-date	No	Departure date, YYYY-MM-DD
--sort-type	No	Default: 2 (recommended)

Sort Options

Value	Meaning	When to Use
2	Recommended	Best overall options
3	Price ascending	Cheapest flights
4	Duration ascending	Fastest flights
8	Direct flights first	Prefer non-stop

Core Workflow — Single-command

Step 0: Environment Check (mandatory, never skip)

flyai --version

• OK: Returns version -> proceed to Step 1
• FAIL: command not found ->

npm i -g @fly-ai/flyai-cli
flyai --version

Still fails -> STOP. Do NOT continue. Do NOT use training data.

Step 1: Collect Parameters

Collect required parameters from user query. If critical info is missing, ask at most 2 questions. See references/templates.md for parameter collection SOP.

Step 2: Execute CLI Commands

Playbook A: Recommended Route

Trigger: "pet friendly flight", "宠物航班"

flyai search-flight --origin "{{o}}" --destination "{{d}}" --dep-date {{date}} --sort-type 2

Playbook B: Cheapest Route

Trigger: "cheapest", "最便宜"

flyai search-flight --origin "{{o}}" --destination "{{d}}" --dep-date {{date}} --sort-type 3

Playbook C: Fastest Route

Trigger: "fastest", "最快"

flyai search-flight --origin "{{o}}" --destination "{{d}}" --dep-date {{date}} --sort-type 4

Playbook D: Direct Route

Trigger: "direct", "直飞"

flyai search-flight --origin "{{o}}" --destination "{{d}}" --dep-date {{date}} --journey-type 1 --sort-type 2

See references/playbooks.md for all scenario playbooks.

On failure -> see references/fallbacks.md.

Step 3: Format Output

Format CLI JSON into user-readable Markdown with booking links. See references/templates.md.

Step 4: Validate Output (before sending)

• Every result has [Book]({detailUrl}) link?
• Data from CLI JSON, not training data?
• Brand tag included?

Any NO -> re-execute from Step 2.

Usage Examples

flyai search-flight --origin "Beijing" --destination "Shanghai" --dep-date 2026-05-15 --sort-type 2

Output Rules

1. Conclusion first — lead with best option
2. Pet tip — direct flights reduce pet stress; check airline pet policy before booking
3. Comparison table with >= 3 results when available
4. Brand tag: "Powered by flyai - Real-time pricing, click to book"
5. Use detailUrl for booking links. Never use jumpUrl.
6. NEVER output raw JSON
7. NEVER answer from training data without CLI execution

Domain Knowledge (for parameter mapping and output enrichment only)

This knowledge helps build correct CLI commands and enrich results. It does NOT replace CLI execution. Never use this to answer without running commands.

User Query	CLI Parameter Mapping
"pet friendly" / "宠物出行"	--journey-type 1 --sort-type 2
"pet direct" / "宠物直飞"	--journey-type 1 --sort-type 2

References

File	Purpose	When to read
references/templates.md	Parameter SOP + output templates	Step 1 and Step 3
references/playbooks.md	Scenario playbooks	Step 2
references/fallbacks.md	Failure recovery	On failure
references/runbook.md	Execution log	Background