skills.rest
project-ax
project-axOFFICIAL
Explore all skills by this author →
GitHub

provider-web

Fetch web pages and search via Tavily with DNS pinning and taint tagging.

5|2|Updated Feb 8, 2026
Search Tags:#security#web search#http fetch#dns pinning#taint tagging#web access
One-click install
npx skills add https://github.com/project-ax/ax --skill provider-web
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: provider-web
Source: https://github.com/project-ax/ax/tree/main/.claude/skills/ax/provider-web
Command: npx skills add https://github.com/project-ax/ax --skill provider-web

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and scripts (resource) components.

What problem does it solve?

This Skill provides a secure and controlled mechanism for AI agents to access web content, preventing common security vulnerabilities like DNS rebinding and SSRF.

Core Features & Use Cases

  • Secure HTTP Fetch: Fetches web pages with DNS pinning and private IP blocking.
  • Web Search: Integrates with Tavily for web search and page content extraction.
  • Taint Tagging: Automatically tags all web responses as 'external' for security.
  • Use Case: An agent needs to research a current event. It uses the provider-web skill to search for news articles and then fetch the content of the most relevant ones, ensuring all network access is mediated and safe.

Quick Start

Use the provider-web skill to search the web for 'latest advancements in AI'.

Frequently Asked Questions about provider-web

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I prevent SSRF and DNS rebinding when an AI agent fetches web pages?▼

Secure web access for agents prevents SSRF by routing HTTP fetch operations through a proxy with DNS pinning and private IP blocking. This stops malicious requests from reaching internal endpoints via manipulated domain resolutions.

What is taint tagging for external web data in AI agents?▼

Taint tagging for external web data is a security mechanism that automatically marks all web search and HTTP fetch responses as external. This ensures agents process untrusted web content with appropriate security boundaries.

How do I securely integrate web search and page extraction into an AI agent?▼

You can securely integrate web search and page extraction by using a provider that operates via IPC and integrates with the Tavily SDK. This prevents direct agent network access while returning tagged search results.

Can AI agents perform web searches without direct network access?▼

Yes, AI agents can perform web searches without direct network access by using an IPC-based proxy architecture. All web search and page extraction requests are mediated by the provider, preventing direct outbound connections from the agent.

Does secure HTTP fetch for agents block private IP addresses?▼

Yes, secure HTTP fetch for agents blocks private IP addresses to mitigate SSRF risks. Combined with DNS pinning, it ensures that resolved domains do not redirect agent traffic to unauthorized internal network resources.

Related Skills

Explore More Software Engineering Skills→
tharunramagiritharunramagiri

add-whatsapp-cloud

Integrate the Meta WhatsApp Business Cloud API for 1:1 messaging.

Community
Intermediate
YukiIto1999YukiIto1999

performing-network-traffic-analysis-with-tshark

Analyze PCAP files with tshark to extract protocol statistics, top talkers, DNS queries, HTTP URLs, and IOCs.

Community
Intermediate
XPRNetworkXPRNetwork
3

web-scraping

Fetch web pages and extract clean text, titles, and links.

Official
Intermediate
marquesfelipmarquesfelip

ssrf-protection

Validate outbound HTTP requests to block SSRF and private network access.

Community
Advanced