Skill flagged — suspicious patterns detected

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

explore-vietnam

v3.2.0

Book flights to Vietnam including Hanoi, Ho Chi Minh City, and Da Nang. Also supports: flight booking, hotel reservation, train tickets, attraction tickets,...

0· 56·0 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-vietnam.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "explore-vietnam" (palexu/explore-vietnam) from ClawHub.
Skill page: https://clawhub.ai/palexu/explore-vietnam
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-vietnam

ClawHub CLI

Package manager switcher

npx clawhub@latest install explore-vietnam
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Suspicious
medium confidence
!
Purpose & Capability
Name/description promise flights, hotels, trains, attractions, visa/insurance, etc., but the runtime instructions only implement flight searches via a single CLI (flyai). The description also claims 'Powered by Fliggy (Alibaba Group)' while the CLI and brand tag are 'flyai'—a branding mismatch. These inconsistencies mean the declared capabilities do not match what the skill actually does.
Instruction Scope
SKILL.md tightly constrains outputs to the flyai CLI and forbids using training data, which is consistent for a CLI-driven skill. However, it instructs the agent to install a global npm package at runtime if the CLI is missing, and contains a 'self-test' loop that forces re-execution until [Book](...) links appear — that could lead to repeated installs or looping behavior. There are also mismatches between parameter lists and templates (templates reference flags like --max-price and --seat-class-name that are not listed in the Parameters table).
!
Install Mechanism
The skill is instruction-only (no install spec), but runtime instructions explicitly tell the agent to run `npm i -g @fly-ai/flyai-cli` if the CLI is absent. Installing a global npm package is a potentially impactful action (writes to the host environment) and the package origin isn't linked to an official homepage in the skill metadata. This is a moderate-risk install action because the skill will attempt to fetch and execute code from the public npm registry at runtime.
Credentials
The skill declares no required environment variables, no config paths, and its instructions do not request credentials. That is proportionate for a flight-search wrapper. However, the skill's broader description (hotels, insurance, etc.) would typically require additional integrations/credentials if they were implemented—those are not present, which underscores the capability mismatch noted above.
Persistence & Privilege
always is false and there are no install specs that modify other skills or system-wide settings. The skill does instruct creating logs (runbook) and global npm install at runtime, but it does not request permanent presence or elevated platform privileges in the metadata.
What to consider before installing
Key points to consider before installing or enabling this skill: - Capability mismatch: The description advertises hotels, trains, tickets, visa and insurance help, but the instructions only perform flight searches via a CLI. Expect flight-only behavior despite broader claims. - Branding and parameter inconsistencies: The description mentions Fliggy while the CLI and brand tag say 'flyai'; templates mention flags (--max-price, --seat-class-name) that the Parameters table does not list. Ask the publisher to clarify source and supported flags. - Runtime global install: The skill will attempt to run `npm i -g @fly-ai/flyai-cli` if the CLI is missing. Global npm installs modify the host environment—verify the npm package identity, inspect the package on the npm registry, and avoid allowing global installs in sensitive environments. - Potential looping: The 'self-test' requiring a [Book](...) link and instructions to re-execute could cause repeated CLI runs; limit retries or require manual confirmation before repeated actions. - No homepage/source provided: The skill metadata lacks a homepage or source repository. Prefer skills with a verifiable source and review the upstream CLI repo or npm package before trusting it. - Safety steps: (1) Review the @fly-ai/flyai-cli package on npm/GitHub and its maintainers; (2) test the skill in an isolated sandbox/VM where npm global installs are safe; (3) restrict or audit network and filesystem permissions for the agent; (4) require explicit user approval before the agent performs installations or repeated CLI calls. If the publisher can provide a clear homepage, source repo, and documentation for the CLI showing the exact flags used, that would raise confidence. Without that, treat the skill as potentially risky and limit its ability to modify the host environment or run autonomously.

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

latestvk976zxz81pxrxp4b4mkryaeje985fqqa
56downloads
0stars
1versions
Updated 3d 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-vietnam

Overview

Explore Vietnam.

When to Activate

User query contains:

  • English: "vietnam flight", "hanoi flight", "ho chi minh flight", "saigon flight", "da nang flight"
  • Chinese: "越南航班", "河内机票", "胡志明机票", "岘港机票", "去越南"

Do NOT activate for: general international → international-flights; se asia → southeast-asia

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: "vietnam flight", "越南航班"

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. Vietnam tip — visa on arrival for Chinese citizens; affordable destination
  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
"vietnam" / "越南"--sort-type 2
"cheap vietnam" / "便宜越南机票"--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...