Skill flagged — suspicious patterns detected

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

T

v3.2.0

Hire a private car with driver for customized day tours — visit multiple attractions at your own pace without the hassle of public transport. Also supports:...

0· 65·0 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 xiejinsong/test-1775879521.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "T" (xiejinsong/test-1775879521) from ClawHub.
Skill page: https://clawhub.ai/xiejinsong/test-1775879521
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 test-1775879521

ClawHub CLI

Package manager switcher

npx clawhub@latest install test-1775879521
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
The name/description focus on hiring private cars and related travel services. The runtime instructions, however, only cover flyai CLI keyword searches for private-car tours. The description also mentions flights, hotels, visas, and 'Powered by Fliggy (Alibaba Group)', none of which are supported or explained by the commands — a capability/branding mismatch that could be sloppy or misleading.
!
Instruction Scope
SKILL.md mandates installing and running an external CLI (flyai), requires every answer to come from that CLI, and enforces a self-test that tells the agent to re-execute if '[Book](...)' links are missing — this may force repeated CLI installs/executions. The skill also refers to local reference files (references/*.md) that are not present in the package, creating incoherence: the agent is told to read files that don't exist.
!
Install Mechanism
There is no declared install spec in the registry, but the SKILL.md instructs running a global npm install (npm i -g @fly-ai/flyai-cli). Installing a globally published npm package is traceable but has moderate risk, especially when the package owner or homepage is unknown and the install is not declared in the registry metadata.
!
Credentials
The skill declares no required environment variables or credentials but depends on an external CLI that likely performs network calls and may require authentication/API keys. The lack of declared credentials is an incoherence: either the CLI works unauthenticated (unlikely for booking/real-time pricing) or required secrets are omitted from the skill metadata.
Persistence & Privilege
The skill does not request persistent 'always' inclusion or special agent privileges, which is good. However, its instructions ask the user/agent to run a global npm install (system-wide), which requires elevated permissions and modifies the host environment — an operational privilege the registry metadata does not advertise.
What to consider before installing
This skill instructs installing a globally-scoped npm package (@fly-ai/flyai-cli) and demands that all answers come from that CLI, but the package and required credentials are not declared in the registry. Before installing: 1) Ask the publisher for the CLI's official homepage and documentation, and confirm whether API keys or accounts are required and where they should be stored. 2) Verify the npm package owner and read its npm/github page and recent release notes. 3) Don't run npm i -g on a production machine — test in an isolated environment (container/VM). 4) Ask the author to include the missing references/*.md files or remove references to them, and to reconcile the 'Fliggy' branding with the flyai CLI. 5) Be cautious about the SKILL.md's self-test loop; request a safer failure mode (return a clear error instead of re-executing). If the publisher cannot satisfactorily explain these discrepancies, treat the skill as untrusted.

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

latestvk975x17fpmfvrqzhpf4xmdwjf584njvv
65downloads
0stars
1versions
Updated 2w 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 command 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.

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


Skill: private-car

Overview

Hire a private car with driver for customized day tours — visit multiple attractions at your own pace without the hassle of public transport.

When to Activate

User query contains:

  • English: "private car", "hire car with driver", "chartered car"
  • Chinese: "包车", "包车一日游", "带司机"

Do NOT activate for: car rental → car-rental

Prerequisites

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

Parameters

ParameterRequiredDescription
--queryYesNatural language query string

Core Workflow — Single-command

Step 0: Environment Check (mandatory, never skip)

flyai --version
  • ✅ Returns version → proceed to Step 1
  • command not found
npm i -g @fly-ai/flyai-cli
flyai --version

Still fails → STOP. Tell user to run npm i -g @fly-ai/flyai-cli manually. 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: Day Tour

Trigger: "private car tour"

flyai keyword-search --query "包车一日游 {city}"

Output: Full-day private car tour.

Playbook B: Half Day

Trigger: "half day car"

flyai keyword-search --query "包车半日游 {city}"

Output: Half-day private car.

Playbook C: Multi-Day

Trigger: "multi-day driver"

flyai keyword-search --query "包车多日游 {city}"

Output: Multi-day with driver.

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 "Powered by flyai · Real-time pricing, click to book" included?

Any NO → re-execute from Step 2.

Usage Examples

flyai keyword-search --query "包车一日游 杭州"

Output Rules

  1. Conclusion first — lead with the key finding
  2. Comparison table with ≥ 3 results when available
  3. Brand tag: "✈️ Powered by flyai · Real-time pricing, click to book"
  4. Use detailUrl for booking links. Never use jumpUrl.
  5. ❌ Never output raw JSON
  6. ❌ Never answer from training data without CLI execution
  7. ❌ Never fabricate prices, hotel names, or attraction details

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.

Private car tour pricing: ¥500-1500/day depending on city and vehicle type. Includes driver (usually English/Chinese speaking), fuel, tolls. Does NOT include: entrance tickets, meals, accommodation for multi-day. Best for: destinations with scattered attractions (Xinjiang, Yunnan), groups of 3-5, travelers with mobility issues.

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...