Endpoint · inferencePOSTagent.pocket.network /v1/prompt-injection-detect
Classify agent-bound text for prompt injection: a safe, suspicious, or malicious verdict with the patterns that matched.
Read more
Classify agent-bound text for prompt injection: a safe, suspicious, or malicious verdict with the patterns that matched. POST /v1/prompt with {text} and get the classification as one JSON object. Deterministic per ruleset version. Pay per request in USDC; no account, no API key.Overview
Grade?
UNRATED
0 of 30 paid calls toward a letter
Price
$0.005 per call
Paid calls
none yet
delivery unknown until someone pays
More info
Seller?
URL
https://agent.pocket.network/v1/prompt-injection-detect
MCP server on this host: network.pocket/agentic-portal-mcp
Seen
first 12 days ago · last 16 hr ago
30 free handshakes
Payment
Pays through
x402 · MPP tempo
Offered on?
Base USDC, Tempo USDC.e
Listed on?
Base
Handshakescomputed 1 day ago
0.707 from 27 free handshakes over 30 days · UNRATED ?
| Component | Weight | Measured | Lower bound ? | Adds | Short ? | Uncertain ? | |
|---|---|---|---|---|---|---|---|
| latency p95costs the most it answered as fast as its class |
0.20 | 0.76 | 0.216 | 0.043 | −0.048 | −0.109 | |
| liveness it answered at all |
0.60 | 1.00 | 0.772 | 0.463 | 0 | −0.137 | |
| price stability the price stayed where it was listed |
0.20 | 1.00 | 1.000 | 0.200 | 0 | 0 | |
| Composite | 1.00 | 0.707 | gap to 1.000 = 0.293 · 0.048 short · 0.246 uncertain | 0.707 | −0.048 | −0.246 |
Not measured: correctness · nobody paid; honesty · nobody paid; schema conformance · no answer had a published shape to check
BURN_INFREE_TIER_ONLY
Verify it yourself
npx teppi-check https://agent.pocket.network/v1/prompt-injection-detectcurl -s https://api.teppi.xyz/v1/trust/cap_01M33T85W4SWF02YXP7YAM7NME