Web Research logo

Web Research

Organization
oasm-platform
web-research

Perform web research using CVE databases, security advisories, and threat intelligence sources. Use when the user asks about CVEs, security news, vulnerabilities, patch releases, or any external security information not available in the workspace.

Overview

Publisheroasm-platform
Repositoryopen-asm
Skill nameweb-research
Stars
192
Forks
30
Bundled files
Instructions only
LicenseGPL-3.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by oasm-platform on GitHub. Read the source before you install it.

Installation

Install the Web Research AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/oasm-platform/open-asm.git /tmp/open-asm
mkdir -p .claude/skills
cp -r /tmp/open-asm/core-api/src/modules/agents/skills/web-research .claude/skills/web-research
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Web Research in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Web Research on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Web Research is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Web Research

Use this skill when you need to find external security information that is not already in the OASM platform.

When to Use

  • User asks about a specific CVE (e.g., "what is CVE-2024-1234?")
  • User asks about recent vulnerabilities or exploits
  • User wants to know about patch releases or security advisories
  • User asks about industry-specific threats or news
  • User needs context about a technology or software vulnerability

Core Tool: retrieve_web_page

Use retrieve_web_page to fetch content from any public URL. It returns statusCode and body.

retrieve_web_page({ url: "https://example.com/path" })

Always use retrieve_web_page instead of trying to construct fetch requests manually. It handles User-Agent headers and error handling automatically.

Workflow

1. Identify What You Need

Before fetching, know what information you're looking for:

  • CVE details → fetch from Trickest/NVD
  • Exploit PoC → fetch from GitHub/Exploit-DB
  • Vendor patches → fetch from vendor advisory pages
  • Threat news → fetch from security news sites

2. Build the URL

Pick the right source for the query:

Query TypeSourceURL Pattern
CVE detailsTrickest CVEhttps://raw.githubusercontent.com/trickest/cve/refs/heads/main/{YEAR}/CVE-{YEAR}-{NUMBER}.md
CVE details (alt)NVD APIhttps://services.nvd.nist.gov/rest/json/cves/2.0?cveId=CVE-{YEAR}-{NUMBER}
Microsoft CVEMSRChttps://msrc.microsoft.com/update-guide/vulnerability/CVE-{YEAR}-{NUMBER}
Exploit codeGitHubhttps://github.com/search?q={QUERY}+exploit&type=repositories
Exploit modulesExploit-DBhttps://www.exploit-db.com/search?q={QUERY}
Metasploit modulesRapid7https://www.rapid7.com/db/modules/?q={QUERY}
Apache advisoriesApache Mailing Listshttps://lists.apache.org/
Package vulnerabilitiesnpmhttps://www.npmjs.com/advisories
Package vulnerabilitiesPyPIhttps://pypi.org/security/

3. Fetch and Analyze

  1. Call retrieve_web_page with the constructed URL
  2. Parse the body content — extract relevant sections
  3. If the page has links to related content, fetch up to 3-5 linked pages for comprehensive analysis
  4. Synthesize findings from multiple sources

4. Correlate with Workspace

After gathering external intel, map findings back to the workspace:

  • Use enumerate_assets or fingerprint_technologies to check if affected software is in use
  • Use discover_vulnerabilities to see if the CVE is already tracked
  • Use enumerate_open_issues to check if someone is already investigating

5. Save Important Findings

  • Use stm_write to store research results for the current conversation
  • Use ltm_append to persist critical threat intelligence

Query Tips

  • Include version numbers: "Apache 2.4.49 path traversal" not just "Apache vulnerability"
  • Include year for CVEs: "CVE-2024-1234" narrows results
  • Use specific terms: "Log4Shell RCE" not "Log4j issue"
  • For zero-days, search for the vendor advisory page directly

Frequently asked questions

What does the Web Research AI skill do?

Perform web research using CVE databases, security advisories, and threat intelligence sources. Use when the user asks about CVEs, security news, vulnerabilities, patch releases, or any external security information not available in the workspace.

Why use Web Research on TypingMind?

Because you install it once and use it with any model. Web Research is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Web Research in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/oasm-platform/open-asm/tree/main/core-api/src/modules/agents/skills/web-research. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Web Research?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Web Research?

As many as you like. As long as a model supports skills, you can use Web Research with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Web Research AI skill free?

Yes. It is published on GitHub by oasm-platform under the GPL-3.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇