ToolVet
57trust / 100

Fetch

by SafeFetch in Search & web

x402 APIPassing, checked 3 h ago

Fetch a public web page and return clean Markdown with stable citation anchors, a content hash, and a retrieval timestamp — plus evidence of hidden text, invisible Unicode, and prompt-injection attempts found in the page. Strict SSRF protection on every redirect hop. Returns a per-span verdict with the decoded payload, not a confidence score. Zero retention.

POST
https://safefetch.schemasure.com/v1/fetch
Price
$0.02
per call in USDC
Uptime
100%
last 30 days
Response time
405 ms
1.4 s slowest 5%
Last check
Passed
3 h ago, next in 3 h

Run a free test callHow to call it

This listing's own text contains instructions aimed at AI agents (see the security scan below). We withhold that text from agents and never recommend this service.

Reliability

All checks passedSome failedAll failedNot checked

Status and outage history · Atom feed · Watch with other listings

How to call it

POST https://safefetch.schemasure.com/v1/fetch

Each call costs $0.02 in USDC on Base, paid with the request over x402.

Run a free test callOne unpaid request, the way an agent sends it. You see the payment challenge it gets back. Nothing is charged.

Example request

From the listing.

POST https://safefetch.schemasure.com/v1/fetch
content-type: application/json

{
  "output": "markdown",
  "policy": {
    "allow_redirects": 3,
    "flag_prompt_injection": true,
    "max_bytes": 2000000,
    "respect_robots": true,
    "user_initiated": false
  },
  "url": "https://example.com/article"
}

Parameters

ParameterTypeRequiredDescription
outputstringNoWhich rendering to include in the result. Defaults to markdown. One of: markdown, text, both. Default: "markdown".
policyobjectNo
urlstring (uri)YesAn http or https URL naming a hostname. Ports other than 80 and 443, credentials in the URL, and literal IP addresses are rejected.

Example response

Withheld: the listing's example response contains instructions aimed at AI agents. See the security scan below.

Call it from code

The curl command shows the payment challenge.

curl: see the payment challenge
# bash or zsh: see the payment challenge. Nothing is charged.
curl -sS -g -i -X POST 'https://safefetch.schemasure.com/v1/fetch' \
  -H 'content-type: application/json' \
  --data-raw '{"output":"markdown","policy":{"allow_redirects":3,"flag_prompt_injection":true,"max_bytes":2000000,"respect_robots":true,"user_initiated":false},"url":"https://example.com/article"}'

# x402 v2 sends the challenge base64-encoded in the PAYMENT-REQUIRED header (v1 sends it in the body).
# To read the header:
curl -sS -g -o /dev/null -D - -X POST 'https://safefetch.schemasure.com/v1/fetch' \
  -H 'content-type: application/json' \
  --data-raw '{"output":"markdown","policy":{"allow_redirects":3,"flag_prompt_injection":true,"max_bytes":2000000,"respect_robots":true,"user_initiated":false},"url":"https://example.com/article"}' \
  | grep -i '^payment-required:' | cut -d' ' -f2 | tr -d '\r' | base64 --decode

We don't show code that pays this service: its listing contains instructions aimed at AI agents.

Security scan

2 findings

  • Tries to override the agent's instructions in example_output
    e":"CSS_HIDDEN_TEXT","data":{"excerpt":"ignore all previous instructions","technique":"display-none"},"detail":"display:none block contains
  • Charges more than its listed price in payment
    Listed at $0.01, charges $0.02

Recent checks

WhenResultHTTPTimePrice
3 h agoPassed402408 ms$0.02
12 h agoPassed402340 ms$0.02
21 h agoPassed402399 ms$0.02
32 h agoPassed402319 ms$0.02
42 h agoPassed402382 ms$0.02
Show 10 older checks
2 days agoPassed402372 ms$0.02
3 days agoPassed402361 ms$0.02
3 days agoPassed402428 ms$0.02
3 days agoPassed402418 ms$0.02
4 days agoPassed402354 ms$0.02
4 days agoPassed402421 ms$0.02
4 days agoPassed4022.5 s$0.02
4 days agoPassed402290 ms$0.02
5 days agoPassed402405 ms$0.02
5 days agoPassed402416 ms$0.02

History

11 Oct 2026Price changed from $0.01 to $0.02