Prompt-injection guard for agents

unreachable

Pre-flight check for untrusted text before an AI agent reads it (web pages, emails, tool output, documents): verdict safe / suspicious / malicious, 0-100 score and every finding with the matched span. Detects instruction overrides (8 languages), fake system/chat tokens, authority and pre-authorisation claims, secret and wallet-fund exfiltration, hidden text (Unicode tags, zero-width, HTML…

AIBasex402 v2exactguard.genexxis.com ↗︎

Settled via Coinbase.

Transactions · 30d
320
Volume · 30d
$1.98
Unique buyers · 30d
7
Uptime · 30d
50.0%
Latency p50
395ms
Reported calls · 30d
6

Endpoints (2 live)

  • POST /check — Classify text an AI agent is about to read for prompt injection: verdict (safe, suspicious, malicious), score 0-100, findings with matched spans; decodes hidden Unicode tags, HTML comments, CSS-hidden text and base64 before scanning. (0.002 USDC on Base)
  • GET /check (free)

First seen · last seen · last active