safe-web

Web & Frontend Development
v1.0.8
Benign

Secure web fetch and search with **PromptGuard** scanning.

11.2K downloads1.2K installsby @adamnaghs

Setup & Installation

Install command

clawhub install adamnaghs/safe-web

If the CLI is not installed:

Install command

npx clawhub@latest install adamnaghs/safe-web

Or install with OpenClaw CLI:

Install command

openclaw skills install adamnaghs/safe-web

or paste the repo link into your assistant's chat

Install command

https://github.com/openclaw/skills/tree/main/skills/adamnaghs/safe-web

What This Skill Does

Wraps web fetch and search operations with PromptGuard scanning to detect prompt injection attacks hidden in web content. Any page or search result that fails the scan is blocked before it enters the AI context window. Operates fail-closed: if scanning cannot run, the tool returns an error rather than unverified content.

Native web fetch tools return content without injection scanning, so malicious pages can silently alter AI behavior without detection.

When to Use It

  • Fetching articles from unfamiliar or untrusted URLs
  • Scraping competitor or news sites without exposing the AI to injected instructions
  • Searching the web during automated research pipelines
  • Processing user-supplied URLs in an AI agent workflow
  • Auditing web pages suspected of containing embedded injection attempts

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: Fetching articles from unfamiliar or untrusted URLs

AGENT
  1. 1Fetching articles from unfamiliar or untrusted URLs
  2. 2Scraping competitor or news sites without exposing the AI to injected instructions
  3. 3Searching the web during automated research pipelines
  4. 4Processing user-supplied URLs in an AI agent workflow
  5. 5Auditing web pages suspected of containing embedded injection attempts
OUTPUT
Secure web fetch and search with **PromptGuard** scanning.

Share this skill

Security Audits

VirusTotalBenign
OpenClawBenign
View full report

These signals reflect official OpenClaw status values. A Suspicious status means the skill should be used with extra caution.

Details

LanguageMarkdown
Last updatedFeb 25, 2026