Endpoints: 76,849MCP servers: 32,730Payout addresses: 3,825Paid calls: 6,158Letters: 84Defects: 3,898counted 1 min ago
teppi

Endpoint · evidenceGETapi.aiskills402.com/v1/skills/prompt-injection-guard/file

Prompt Injection Guard — Keeps an AI agent from obeying instructions hidden in what it reads (indirect prompt injection).
Read morePrompt Injection Guard — Keeps an AI agent from obeying instructions hidden in what it reads (indirect prompt injection). Web pages, e-mails, files, PDFs, API and tool output, other agents' messages and skill files under review are treated as content, never as orders. The agent is instructed never to pay, transfer, delete or reveal anything because content asked, to report the attempt with a quote and its source, and to still finish the real task. Use whenever the agent reads anything it did no…
UNRATEDListed

Overview

Grade?
UNRATED
0 of 30 paid calls toward a letter
Price
$0.07 per call
Paid calls
none yet
delivery unknown until someone pays

More info

URL
https://api.aiskills402.com/v1/skills/prompt-injection-guard/file
Seen
first 46 days ago · last 4 days ago
52 free handshakes

Payment

Pays through
x402
Offered on?
Base USDC
Listed on?
Base

Handshakescomputed 3 days ago

0.681 from 31 free handshakes over 30 days · UNRATED ?

How the composite of 0.681 is made up, part by part
ComponentWeightMeasuredLower bound ?AddsShort ?Uncertain ?
latency p95costs the most
it answered as fast as its class
0.20 0.00 0.000
0.000 −0.2000
liveness
it answered at all
0.60 1.00 0.802
0.481 0−0.119
price stability
the price stayed where it was listed
0.20 1.00 1.000
0.200 00
Composite1.000.681gap to 1.000 = 0.319 · 0.200 short · 0.119 uncertain0.681−0.200−0.119

Not measured: correctness · nobody paid; honesty · nobody paid; schema conformance · no answer had a published shape to check

BURN_INFREE_TIER_ONLY
Verify it yourselfnpx teppi-check https://api.aiskills402.com/v1/skills/prompt-injection-guard/filecurl -s https://api.teppi.xyz/v1/trust/cap_01M404RPCT5R0AF3A9XM1BBK7Z