web info skill

Extract and display useful information from web pages including title, meta description, headers, and links.

Security Scan

The skill implements a simple curl-based web scraper that matches its stated purpose, but its runtime instructions make stronger privacy/security claims (e.g., honoring robots.txt, only fetching public pages) that the included script does not enforce, creating a notable mismatch and potential risk (SSRF/internal fetches).

Purpose & Capability

Name, description, and required binary (curl) align with the bundled bash script: a lightweight HTML extractor that pulls title, headers, links, images, and stats.

Instruction Scope

SKILL.md claims 'Follows robots.txt directives' and 'Only fetches publicly accessible pages', but web-info.sh performs a straight curl on any http(s) URL provided and contains no robots.txt checks or host access restrictions. That mismatch could allow fetching internal or non-public endpoints (SSRF-like risks).

Install Mechanism

Instruction-only with a small bash script; no install spec or remote downloads. No files are written to disk beyond running the script in-memory—low install risk.

Credentials

No environment variables, credentials, or config paths are requested. The requested surface (curl only) is proportionate to the stated function.

Persistence & Privilege

Skill is not always-on and is user-invocable; it does not request elevated privileges or modify other skills or system-wide configs.

What to consider before installing

The code appears to do what the README and description say, but the documentation overstates safety guarantees. Before installing or enabling: 1) note that the script does not honor robots.txt or restrict hosts — it will curl any http(s) URL you pass (including internal addresses like 127.0.0.1 or intranet hosts), which can be abused for SSRF or to access non-public resources; 2) review and run the script in a sandboxed environment or with network egress restrictions if you want to limit exposure; 3) if you need robots.txt compliance or host allowlists, add explicit checks (fetch and parse robots.txt, validate hostname/IP ranges) or reject non-public hosts; 4) be aware output may include sensitive content from fetched pages; 5) if you want stronger guarantees, ask the publisher to remove the misleading privacy/security claims or to implement robots.txt and host restrictions.

Web Info Extractor

A lightweight web scraping skill that extracts structured information from any webpage.

Features

• Extract page title and meta description
• List all headers (H1-H6)
• Extract all links with their anchor text
• Display images and their alt text
• Show page word count
• JSON output support for easy parsing

Usage

# Basic usage
web-info https://example.com

# Get JSON output
web-info --json https://example.com

# Extract only links
web-info --links-only https://example.com

# Extract only headers
web-info --headers-only https://example.com

Examples

Extract page info

web-info https://news.ycombinator.com

Get structured JSON data

web-info --json https://github.com > github-info.json

Find all links on a page

web-info --links-only https://example.com

Output Format

The skill provides clean, formatted output:

Title: Example Domain
Description: Example meta description
URL: https://example.com

Headers:
  H1: Example Domain
  H2: More information

Links:
  - Example Link (https://example.org)
  - Another Link (https://example.net)

Images:
  - logo.png (alt: "Company Logo")

Statistics:
  - Word count: 150
  - Links: 5
  - Images: 2

Requirements

• curl (for fetching web pages)

Privacy & Security

• Does not store any data
• Only fetches publicly accessible pages
• Follows robots.txt directives
• No cookies or authentication stored

License

MIT-0 - Free to use, modify, and distribute