Skills/PyPI/sitecheck-mcp

sitecheck-mcp@0.1.0

CAUTION· not started

Publisher claims: "MCP server that assesses whether a website is legitimate or a scam, from registration, TLS, reputation feeds, look-alike analysis and page content" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher snickery · publishing for 105 daysInstalls 195Last detonated 1 h ago

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
ABUSECH_AUTH_KEYMCP_BEARER_TOKENSAFE_BROWSING_API_KEYURLSCAN_API_KEYVIRUSTOTAL_API_KEYConfiguration, not credentials: ABN_LOOKUP_GUID, SITECHECK_CACHE_DIR, SITECHECK_TRANCO_TOP_N, SITECHECK_USER_AGENT
Where it talks to
no vendor host named in the codeAlso abuse.ch, tranco-list.eu, githubusercontent.com, openphish.com, rdap.org, crt.sh, archive.org, virustotal.com, urlscan.io, business.gov.au — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names abuse.ch, tranco-list.eu, githubusercontent.com, openphish.com, rdap.org, crt.sh, archive.org, virustotal.com, urlscan.io, business.gov.au as well as its own vendor. The guard injects ABUSECH_AUTH_KEY, MCP_BEARER_TOKEN, SAFE_BROWSING_API_KEY, URLSCAN_API_KEY, VIRUSTOTAL_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx sitecheck-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-18 and scored it 77/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Pipe-to-shell pattern. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

CRITICAL
Pipe-to-shell pattern.forgejo/workflows/tests.yml:23 · Pipe-to-shell pattern — downloads and immediately executes remote codecurl -LsSf https://astral.sh/uv/install.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
URL with suspicious TLDtests/test_units.py:27 · URL with suspicious TLD — commonly used for phishing/malwaret = parse_target("https://Login.PayPal.com.verify-acct.top/x?id=abc#f")Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Process kill commandsrc/sitecheck_mcp/healthcheck.py:2 · Process kill command — agent can terminate processesas alive), so HealthOnFailure=kill can restart a wedged event loop."""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
URL with suspicious TLDtests/test_units.py:32 · URL with suspicious TLD — commonly used for phishing/malwareassert t.stripped_url() == "https://login.paypal.com.verify-acct.top/x"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDtests/test_units.py:252 · URL with suspicious TLD — commonly used for phishing/malwarea = analyze_html(PHISH, "https://secure-acct-check.top/login")Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
HTTP URL with a raw public IP addresstests/test_units.py:48 · HTTP URL with a raw public IP address — a hard-coded destination that domain-based monitoring cannot namet = parse_target("http://203.0.113.9/login")Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL using a raw public IP addresstests/test_units.py:48 · URL using a raw public IP address — may bypass domain-based filteringt = parse_target("http://203.0.113.9/login")Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Remote installer piped to shell.forgejo/workflows/tests.yml:23 · Remote installer piped to shellcurl -LsSf https://astral.sh/uv/install.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
URL with suspicious TLDtests/test_client.py:73 · URL with suspicious TLD — commonly used for phishing/malwaret = parse_target("https://login-check.top/x")Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
LOW
URL to a private-network addresstests/test_client.py:33 · URL to a private-network address — a LAN or development targetr = await page.guarded_fetch("http://10.1.2.3/", transport=httpx.MockTransport(lambda req: httpx.Response(200)))Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07

Cost to the agent

Instructions loaded
≈73 tok
1 file · 26 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for sitecheck-mcp@0.1.0 as of 30 min ago. This is the package itself, not its dependencies.

What would make this Verified

3 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  2. Unclaimed publisher≈ +8 on the totalClaim snickery: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. URL with suspicious TLD≈ +2 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  4. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. HTTP URL with a raw public IP address≈ +2 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  6. URL using a raw public IP address≈ +2 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim snickeryPropose a patch to the maintainer