Security checks across malware telemetry and agentic risk
This is a coherent public web research skill, but users should avoid sensitive queries or private URLs because requests may go to search engines and third-party fetch services.
Install only if you intend to use it for public web research. Do not submit confidential search terms, internal URLs, localhost/private-network addresses, credentials, or tokenized links unless you are comfortable with search engines or third-party fetch services receiving them. Use an isolated environment and pin dependencies for repeatable, safer installs.
"Accept": "text/plain",
"X-Return-Format": "markdown",
}
resp = requests.get(
f"https://r.jina.ai/{url}",
headers=headers,
timeout=timeout,try:
import requests
resp = requests.get(
f"https://markdown.new/{url}",
headers={
"Accept": "text/markdown",try:
import requests
resp = requests.get(
f"https://defuddle.md/{url}",
headers={
"Accept": "text/markdown",# Core dependency requests>=2.28.0 # Optional search engines baidusearch>=0.0.1
requests>=2.28.0 # Optional search engines baidusearch>=0.0.1 # Optional fetchers crawl4ai>=0.3.0
baidusearch>=0.0.1 # Optional fetchers crawl4ai>=0.3.0 playwright>=1.40.0 # Optional config support
# Optional fetchers crawl4ai>=0.3.0 playwright>=1.40.0 # Optional config support pyyaml>=6.0
playwright>=1.40.0 # Optional config support pyyaml>=6.0 # Async support aiohttp>=3.9.0
pyyaml>=6.0 # Async support aiohttp>=3.9.0
66/66 vendors flagged this skill as clean.