Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

explore-turkey

v3.2.0

Book flights to Turkey including Istanbul, Cappadocia, and Antalya. Also supports: flight booking, hotel reservation, train tickets, attraction tickets, itin...

0· 62·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for palexu/explore-turkey.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "explore-turkey" (palexu/explore-turkey) from ClawHub.
Skill page: https://clawhub.ai/palexu/explore-turkey
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install explore-turkey

ClawHub CLI

Package manager switcher

npx clawhub@latest install explore-turkey
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
The skill's stated purpose is booking travel to Turkey and that generally aligns with executing a travel-API CLI. However the description claims "powered by Fliggy (Alibaba Group)" while every runtime instruction requires a different tool named 'flyai' (package @fly-ai/flyai-cli). This brand/implementation mismatch is unexplained and could indicate sloppy documentation or misdirection.
!
Instruction Scope
The SKILL.md forces the agent to treat itself as a CLI executor and to never answer from training data — insisting that all answers come from the flyai CLI. It also instructs the agent to install the CLI if missing (npm i -g ...). Because the skill is instruction-only, these installation steps are embedded in runtime instructions rather than in an install spec; that grants the agent broad discretion to run package installs and execute arbitrary CLI commands which go beyond passive data formatting.
!
Install Mechanism
There is no declared install spec in the registry metadata, but the SKILL.md explicitly tells the agent to run `npm i -g @fly-ai/flyai-cli` if the CLI is not present. Installing a global npm package executes code from the npm registry during install and persists a binary on the host. The package name is not a well-known system package in this context and there is no guidance to verify its provenance — this is a moderate-to-high install risk for an instruction-only skill.
Credentials
The skill declares no required environment variables or credentials, which at first seems appropriate. However the SKILL references an external service and a CLI that likely needs authentication or configuration (not documented). The lack of any guidance about how authentication is handled (CLI login, stored tokens, env vars) is an omission that could hide credential requirements or implicit storage of secrets in CLI config files.
!
Persistence & Privilege
Although the skill is not marked always:true and does not request system-wide configuration changes directly, it instructs installing a global CLI (npm i -g) which results in a persistent binary and may write config files (credential/config storage) to the host. The skill does not document where the CLI stores credentials or whether it will modify system PATH or other config, which increases the persistence/privilege risk.
What to consider before installing
Before installing or enabling this skill, consider the following: - Brand mismatch: the description names Fliggy (Alibaba) but the runtime requires a third-party CLI named 'flyai' (@fly-ai/flyai-cli). Ask the publisher which service actually provides flight data and why the docs reference two different brands. - npm install risk: the skill tells the agent to run `npm i -g @fly-ai/flyai-cli` if the CLI is missing. Global npm installs execute code and persist binaries/config on your machine. Only proceed if you (or your administrator) have reviewed the npm package source and trust the publisher. - Authentication & secrets: the skill provides no info about authentication. Ask how the flyai CLI authenticates (interactive login, API key, saved tokens) and where credentials are stored. Avoid supplying cloud or payment credentials until you confirm the auth flow. - Least privilege: if you must test, run the CLI install and execution in a sandboxed environment (container or throwaway VM) and inspect the package contents first (npm view / fetch source) rather than installing on a production system. - If you plan to enable autonomous agent invocation, be extra cautious — autonomous agents running this skill could install the CLI and make network requests without further prompts. If you want, I can: (1) list steps to inspect the npm package before installing, (2) draft questions to ask the skill publisher about the Fliggy vs flyai discrepancy and auth, or (3) suggest safer testing approaches (containerized run).

Like a lobster shell, security has layers — review code before you run it.

latestvk97atxvfwzxjgmmy0aevcg72b585fv1z
62downloads
0stars
1versions
Updated 4d ago
v3.2.0
MIT-0

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: explore-turkey

Overview

Explore Turkey.

When to Activate

User query contains:

  • English: "turkey flight", "istanbul flight", "cappadocia flight", "antalya flight", "turkiye flight"
  • Chinese: "土耳其航班", "伊斯坦布尔机票", "卡帕多奇亚机票", "土耳其旅行", "去土耳其"

Do NOT activate for: general international → international-flights

Prerequisites

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

Parameters

ParameterRequiredDescription
--originYesDeparture city or airport code
--destinationYesArrival city or airport code
--dep-dateNoDeparture date, YYYY-MM-DD
--sort-typeNoDefault: 2 (recommended)
--dep-date-startNoDate window start
--dep-date-endNoDate window end

Sort Options

ValueMeaningWhen to Use
2RecommendedBest overall options
3Price ascendingCheapest flights
4Duration ascendingFastest flights
8Direct flights firstPrefer 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: "turkey flight", "土耳其航班"

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. Turkey tip — e-visa available; Istanbul IST is main hub
  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 QueryCLI Parameter Mapping
"turkey" / "土耳其"--sort-type 2
"cheap istanbul" / "便宜伊斯坦布尔机票"--sort-type 3

References

FilePurposeWhen to read
references/templates.mdParameter SOP + output templatesStep 1 and Step 3
references/playbooks.mdScenario playbooksStep 2
references/fallbacks.mdFailure recoveryOn failure
references/runbook.mdExecution logBackground

Comments

Loading comments...