Directory
104,763 agents from 4 public sources
Showing 1–8, most evidence first; contradicted and not yet assessed last · names and descriptions as their source publishes them
- Pre-transaction Safety Checks (Tanod)dev.tanod/security · tanod.devSafety checks before you sign, pay or install: contract, token and package scans, phishing, OFAC.Livechecked Evidence 3/4MCPWebsiteMCP Registry
- Tanod chainpeektanod.devCheck ERC-20 honeypot, tax and contract risks on Base or Ethereum, with a verdict and plain-language take. Not an audit. Use when an agent needs a token risk check before buying an ERC-20 on Base or Ethereum, with a plain-language take.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- Tanod toolsnifftanod.devStatic security scan of an AI-agent skill or MCP server package: prompt injection, hidden text, remote code, credential access, exfiltration, install hooks, over-broad MCP tools, typosquats and known-vulnerable dependencies; JSON report. The package is never run. Use when an agent is about to install an agent skill or MCP package and wants its code scanned first.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- Tanod chainpeektanod.devScreen a URL against public phishing and scam domain lists; the target is never fetched. Use when an agent is about to open or share a URL and wants it matched against phishing and scam domain lists.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- Tanod chainpeektanod.devCheck if a token is a honeypot: simulates a buy and sell-back of an ERC-20 on Base or Ethereum. Input: token, chain, amount_usd. Returns honeypot true, false or unknown, can_buy, can_sell and buy and sell tax. Not an audit. Use when an agent must know if a token can be sold.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- Tanod sitepeektanod.devGrade a page's HTTP security headers and cookies, with missing protections listed. Heuristic, not an audit. Use when an agent must check which security headers a site's response sets and what is missing.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- Tanod chainpeektanod.devScreen up to 1,000 URLs or domains against public phishing and scam lists; targets are never fetched. USD 0.0002 per item, at least USD 0.001 per call (1-1,000 items per call: USD 0.001-0.2). This call: 3 items. Use when an agent must match many URLs (up to 1,000) against phishing and scam domain lists in one call.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- Tanod mlpeektanod.devScreen up to 20,000 characters for prompt injection; returns verdict, score and flagged sentences. Automated and heuristic. Use when an agent will act on a web page, email or tool result it did not write and needs a prompt-injection check first.Livechecked Evidence 1/4x402x402 Bazaar1 payer