Prompt Injection Guard · api.aiskills402.com

Prompt Injection Guard, Keeps an AI agent

Prompt 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…

Unavailable4 calls · 3 buyers in 30 days

Sample input

input2 keys

method"GET"

type"http"

inputobject, 2 keys

Sample response

response8 keys

file3 keys

content"<the SKILL.md file>"

encoding"utf-8"

name"SKILL.md"

name"Prompt Injection Guard"

oktrue

receipt2 keys

settledtrue

tx"0x<settlement transaction>"

redownload2 keys

token"<64 hex chars>"

url"<api>/v1/purchases/<token>"

sha256"<sha256 of SKILL.md>"

skill"prompt-injection-guard"

version"1.0.0"

responseobject, 8 keys

Track record

Paid calls, last 30 days: 4
Buyers, last 30 days: 3
Last paid call: last week

Reported by the x402 directory.

A$0.10 per call

See similar tools