Travel Information and News

ReviewAudited by ClawScan on May 1, 2026.

Overview

The skill is a coherent travel-search tool, but it relies on external search providers, API keys, optional browser automation, and user-installed dependencies that users should review before use.

This looks like a normal travel-search aggregation skill. Before installing, check that you are comfortable providing Tavily/Brave API keys, sending queries to external search providers, and optionally installing browser automation components. Use the browser-scraping mode only when needed, and prefer a contained environment for Chromium/Puppeteer.

Findings (5)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Low

#ASI03: Identity and Privilege Abuse

What this means

The skill needs third-party search credentials for normal operation; those keys may incur usage, billing, or account-rate-limit effects.

Why it was flagged

The skill requires a Tavily API key and optionally a Brave API key, despite registry metadata declaring no required env vars or primary credential.

Skill content

TAVILY_API_KEY=your_tavily_key_here
BRAVE_API_KEY=your_brave_key_here    # Optional

Recommendation

Use limited-scope API keys where available, store them only in the intended .env file, and review provider billing/rate limits before use.

Low

#ASI07: Insecure Inter-Agent Communication

What this means

Travel queries, client names, itinerary details, or business-sensitive planning terms entered into the skill may be shared with third-party search APIs.

Why it was flagged

User search queries are sent to external search providers; Brave is also used when enabled.

Skill content

requests.post(
            "https://api.tavily.com/search"

Recommendation

Avoid including confidential client or business details in queries unless those providers are approved for that data.

Medium

#ASI02: Tool Misuse and Exploitation

What this means

If browser scraping is enabled, the local environment has more exposure to untrusted web pages than a sandboxed browser would provide.

Why it was flagged

Optional browser scraping launches Chromium with the sandbox disabled, which is common in some automation setups but weakens browser isolation.

Skill content

puppeteer.launch({
    headless: true,
    executablePath: "/usr/bin/chromium",
    args: ["--no-sandbox", "--disable-gpu", "--disable-dev-shm-usage"],
  });

Recommendation

Enable browser scraping only when needed, run it in a contained environment if possible, and avoid using it for sensitive browsing sessions.

Low

#ASI04: Agentic Supply Chain Vulnerabilities

What this means

Installed package versions may vary over time and could introduce compatibility or supply-chain risk.

Why it was flagged

The setup instructions install unpinned packages and optional system/browser tooling, which is expected for this skill but leaves dependency versions to the installation environment.

Skill content

pip install requests fpdf2 python-docx
...
npm install puppeteer

Recommendation

Install from trusted package sources, consider pinning versions in a controlled environment, and review optional browser tooling before installing it.

Low

#ASI05: Unexpected Code Execution

What this means

PDF generation may make an additional network request and place a downloaded font file on the local system.

Why it was flagged

When generating PDFs without a local CJK font, the script downloads a font from GitHub to /tmp for PDF rendering.

Skill content

urllib.request.urlretrieve(url, font_path)

Recommendation

Preinstall a trusted CJK font or verify that downloads from GitHub are acceptable in your environment.