Overview
Agent security guardrail. Judges the pair (untrusted content + proposed action) before an AI agent acts: detects tool calls that obey hidden prompt injection, leave the user's goal, destroy data or send data or money elsewhere. Returns allow, review or block with scores and reasons.
Protocol
L402 (POST)
Price
30 sats
Payment Asset
BTC
Payment Network
Lightning
Category
ai/agents
Provider
Kechlab
Source
self-registered
Indexed
2026-10-18 10:47:25
Health
Status
healthy
Latency (p50)
676ms
Uptime (30d)
100.0%
Reliability Score
87/100
Last Checked
2026-10-22 17:52:28
Last Healthy
2026-10-22 17:52:28
Consecutive Failures
0
Macaroon Format
Format
Not yet detected
Also available via
Recent Health Checks
| Time | Status | HTTP | Latency | Error |
|---|---|---|---|---|
| 2026-10-22 17:52:28 | healthy | 402 | 143ms | |
| 2026-10-22 09:16:09 | healthy | 402 | 676ms | |
| 2026-10-21 21:45:27 | healthy | 402 | 1099ms | |
| 2026-10-21 00:15:18 | healthy | 402 | 505ms | |
| 2026-10-20 13:20:39 | healthy | 402 | 1161ms | |
| 2026-10-20 01:10:12 | healthy | 402 | 432ms |