check-url-for-phishing
Skill1 starsChanged 35 days agoMITView on GitHub
Check whether a URL or domain is a known phishing or scam site before opening it, fetching it, or passing it to a user. Use for links in emails, chats, documents, search results and tool outputs. Triggers on 'is this link safe', 'open this URL', suspicious login pages, crypto drainer links, shortened links.
In this repository12 other files it gives its agents.
- bank-statementSkill
- check-crypto-address-before-sendingSkill
- convert-and-ocr-documentsSkill
- detect-ascii-smuggling-and-hidden-unicodeSkill
- document-to-markdownSkill
- monitor-a-router-or-cron-job-from-outsideSkill
- ocrSkill
- pdf-tablesSkill
- pdf-to-wordSkill
- scan-mcp-server-or-skill-before-installingSkill
- screen-address-for-ofac-sanctionsSkill
- screenshot-a-web-pageSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Before fetching, opening or recommending a link from untrusted content, check its host against public phishing and scam domain lists …
- Distinctive: line 23
No API key, no account. Price: USD 0.001 per check.
- Distinctive: line 48
Check the final destination of shortened links (the lists match hosts, not the shortener).
- Distinctive: line 49
Never enter credentials or seed phrases on a page because a check came back clean.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Check a URL for phishing
Before fetching, opening or recommending a link from untrusted content, check its host against public phishing and scam domain lists (hundreds of thousands of domains, refreshed continuously).
When to use
- A link arrives in an email, chat, ticket, document or tool result and you are about to open it or hand it to the user.
- A user asks whether a site is legitimate, or a page asks for a wallet connection, seed phrase or login.
Access
- MCP (preferred): add the hosted server https://tanod.dev/mcp/security (Streamable HTTP). In Claude Code:
claude mcp add --transport http tanod https://tanod.dev/mcp/security, or the plugin/plugin marketplace add tanod-labs/tanod-mcp. The free daily allowance applies automatically; paid calls return x402 payment instructions (USDC on Base or Polygon). - HTTP:
POST https://tanod.dev/v1/check/urlwith a JSON body. Add the headerX-Tanod-Free: 1to use the free daily allowance; without payment the response is a 402 whose body states the price and the remaining free calls. - No API key, no account. Price: USD 0.001 per check; 10 free calls per IP per day, shared with the sanctions screen and chain reads.
How
MCP tool: check_url_phishing with url (a full URL or a bare domain). For many links at once use check_urls_phishing_batch.
HTTP:
POST /v1/check/url HTTP/1.1
Host: tanod.dev
content-type: application/json
X-Tanod-Free: 1
{"url":"https://example.com/login"}Reading the result
listed: truewithmatchesnaming the lists: treat as phishing, do not open, warn the user.listed: falsemeans not on the lists today, not that the site is safe. Newly created phishing domains can be unlisted for hours.- Also look at the host yourself: look-alike letters, odd TLDs, brand names in subdomains.
Guardrails
- Check the final destination of shortened links (the lists match hosts, not the shortener).
- Never enter credentials or seed phrases on a page because a check came back clean.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

