url-fetcher

GitHub

Warning

1,823stars

Simple web content fetching without API keys or external dependencies. Uses Python stdlib (urllib) only. Features: fetch HTML/text from URLs, basic HTML to markdown conversion, path-validated file writes (blocks system paths), URL validation (blocks localhost/internal). Security: File writes use is_safe_path() to prevent malicious writes. Perfect for content aggregation, research collection, and web scraping without API costs or dependencies.

About

All versions of all skills that are on clawhub.com archived

Quick Start

# Install the skill

$ osk install github:openclaw/skills/skills/johstracke/url-fetcher

# Use with Claude

$ claude --skill url-fetcher

# Use with Codex

$ codex --skill url-fetcher

# Use with Cursor

$ cursor --skill url-fetcher

O

openclaw

View on GitHub

View Source

Repository

openclaw/skills

Stars

1,823

Branch

main

Skill Path

skills/johstracke/url-fetcher/SKILL.md

Also available from

kbarbel640-del/skills

Install Command

$ osk install github:openclaw/skills/skills/johstracke/url-fetcher

Security Audit

v1.1.0

Warnings Found

Score: 78/100 · 4/20/2026

Checks (45 rules)

Data Exfiltration

4 passed

Destructive Commands

8 passed

Credential Access

5 passed

Prompt Injection

4 passed

Network Exfiltration

1 issue

Package Mutation

3 passed

Sensitive Paths

1 issue

Obfuscation

5 passed

Privilege Escalation

4 passed

Tool Permissions

4 passed

Findings (3)

Warningnetwork-ip-address

Contains a raw IP address

Warningpath-ssh

References SSH directory

Infotool-unrestricted

No allowed-tools specified; skill relies on agent defaults (unrestricted tool access)