Lordevo Shop: website checks for agents (x402) D
com.lordevo/shop · v1.2.1 · score 49/100 · checked 2026-11-22
Pay-per-call website checks, web fetch and data tools for AI agents (x402, USDC on Base).
Findings
| Severity | Rule | Detail |
|---|---|---|
| low | AG005 | Remote endpoint lists 64 tool(s) to anyone, no credentials needed. |
| critical | AG101 | tool 'prompt_injection_scan': description contains instruction-like text aimed at the model ('ignore previous instructions'). Possible tool poisoning. |
| medium | AG102 | 1 tool(s) can execute commands or delete data (math_eval). Require confirmation before the agent calls them. |
What was checked
- https://shop.lordevo.com/mcp: answers without auth
Public tools: try_free, site_report, site_report_status, site_check, list_services, get_sample_output, preflight, agent_readiness, url_trust, can_fetch, link_check, dns_lookup, email_validate, ssl_cert, domain_rdap, ip_info, links_batch, broken_links, sitemap_urls, link_preview, readability, structured_data, canonical_check, cors_check, http_ping, domain_lookalike, myr_rates, domain_intel, redirect_chain, text_chunk
Maintainer? Fix, then add the badge
Grades refresh daily.
[](https://agentguard-pi.vercel.app/s/com-lordevo-shop-b47d508e)
agentguard: static and read-only checks. A grade is not a guarantee of safety. Index · Scanner