← All servers

ai.ohmyfin/sanctions F

ai.ohmyfin/sanctions · v1.0.0 · score 0/100 · checked 2026-11-22

Sanctions and export-control screening for AI agents: 320+ watchlists, transliteration, HS and ECCN.

Findings

SeverityRuleDetail
lowAG005Remote endpoint lists 38 tool(s) to anyone, no credentials needed.
criticalAG101tool 'iban_validate': description contains instruction-like text aimed at the model ('do not tell the user'). Possible tool poisoning.
criticalAG101tool 'fx_timing_advisor': description contains instruction-like text aimed at the model ('do NOT tell the user'). Possible tool poisoning.
criticalAG101tool 'transfer_cost': description contains instruction-like text aimed at the model ('do not tell a user'). Possible tool poisoning.

What was checked

Public tools: swift_lookup, iban_validate, country_banking_rules, country_payment_codes, fx_rate, fx_rate_history, gpi_status_codes, swift_message_reference, payment_cutoff_times, fx_volatility, fx_timing_advisor, payment_method_compare, bank_holidays, is_business_day_check, value_date, settlement_eta, transfer_cost, mcp_register, mcp_verify, sanctions_screen, crypto_wallet_screen, crypto_wallet_result, crypto_wallet_report, eccn_lookup, country_export_controls, export_controls_screen, hs_code_lookup, goods_classify, federal_register_changes, track_payment

Maintainer? Fix, then add the badge

Grades refresh daily.

[![agentguard](https://agentguard-pi.vercel.app/badge/ai-ohmyfin-sanctions-a531e3f7.svg)](https://agentguard-pi.vercel.app/s/ai-ohmyfin-sanctions-a531e3f7)

agentguard: static and read-only checks. A grade is not a guarantee of safety. Index · Scanner