Skills/PyPI/xonta-max-mcp

xonta-max-mcp@0.1.0

CAUTION· not started

Publisher claims: "MCP server for building bots and mini-apps for the MAX messenger (max.ru), in English and Russian: current Bot API facts, code checks, Telegram migration, deep links, ad tracking and ROI, test fixtures" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher mrsergeiluzhnov · publishing for 15 daysInstalls 138Last 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
MAX_BOT_TOKENPRIVATE_KEYWEBHOOK_DOMAINWEBHOOK_SECRETWEBHOOK_URLConfiguration, not credentials: ALLOWED_HOSTS, CHATS_FILE, MAX_CA_FILE, MODE, PUBLIC_KEY, STARTS_FILE, XONTA_MAX_HOSTED, XONTA_MAX_LANG
Where it talks to
no vendor host named in the codeAlso max.ru, gu-st.ru, gosuslugi.ru, adindex.ru, ppc.world, yandex.com, unisender.com, sostav.ru, pravo163.ru, example.ru, xonta.ru — not the publisher's domain; check what for before connecting.
What we saw when it ran
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 max.ru, gu-st.ru, gosuslugi.ru, adindex.ru, ppc.world, yandex.com, unisender.com, sostav.ru, pravo163.ru, example.ru, xonta.ru as well as its own vendor. The guard injects MAX_BOT_TOKEN, PRIVATE_KEY, WEBHOOK_DOMAIN, WEBHOOK_SECRET, WEBHOOK_URL only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx xonta-max-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 2026-11-21 and scored it 69/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Privileged sudo command; Destructive file system command detected; Privileged sudo command. 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

HIGH
Privileged sudo commandscripts/deploy_vps.sh:16 · Privileged sudo command — agent may execute with elevated privileges[ -x "$APP/venv/bin/python" ] || sudo -u "$RUN_AS" python3 -m venv "$APP/venv"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedsrc/xonta_max/scaffold.py:23 · Destructive file system command detected&& update-ca-certificates && rm -rf /var/lib/apt/lists/*"""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandscripts/deploy_vps.sh:17 · Privileged sudo command — agent may execute with elevated privilegessudo -u "$RUN_AS" "$APP/venv/bin/pip" install -q --upgrade pipFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandscripts/deploy_vps.sh:12 · File permission modification command — agent changes file ownership/permissionsmkdir -p "$APP" && chown -R "$RUN_AS:$RUN_AS" "$APP"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Destructive file system command detectedDockerfile:9 · Destructive file system command detected&& rm -rf /var/lib/apt/lists/*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandscripts/deploy_vps.sh:18 · Privileged sudo command — agent may execute with elevated privilegessudo -u "$RUN_AS" "$APP/venv/bin/pip" install -q --upgrade "$SRC"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssrc/xonta_max/scaffold.py:19 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesGITIGNORE = ".env\n__pycache__/\n.venv/\nnode_modules/\ndist/\nchats.json\nstarts.jsonl\n"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/xonta_max/scaffold.py:279 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"dev": "tsc && NODE_EXTRA_CA_CERTS=$MAX_CA_FILE node --env-file=.env dist/bot.js",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/xonta_max/server.py:211 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filestr("Заполните .env по .env.example", "Fill in .env from .env.example"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/xonta_max/scaffold.py:219 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files// Запуск: NODE_EXTRA_CA_CERTS=/путь/russian_trusted_root_ca.crt node --env-file=.env dist/bot.jsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandscripts/registry_dns.sh:16 · File permission modification command — agent changes file ownership/permissionsmkdir -p "$DIR" && chmod 700 "$DIR"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathssrc/xonta_max/scaffold.py:450 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files3. Скопируйте `.env.example` в `.env` и заполните.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)scripts/publish.sh:16 · MCP server using network transport (SSE/HTTP) — data sent over networkgh repo edit "$REPO" --add-topic mcp,mcp-server,max,max-messenger,max-bot-api,mini-apps,telegram-migration,russia,model-context-protocolFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
Python subprocess execution detectedtests/test_i18n.py:233 · Python subprocess execution detectedout = subprocess.run([sys.executable, "-c", code], env={**os.environ, "XONTA_MAX_LANG": "en"},Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandscripts/registry_dns.sh:19 · File permission modification command — agent changes file ownership/permissionschmod 600 "$KEY"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Dense URL-encoded contenttests/test_core.py:188 · Dense URL-encoded content — may be obfuscating payloadsassert sh["url"] == "https://max.ru/:share?text=%D0%9F%D1%80%D0%B8%D0%B2%D0%B5%D1%82%20%D0%BC%D0%B8%D1%80%20%26%20co"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
npx invocation of non-well-known packagesrc/xonta_max/scaffold.py:301 · npx invocation of non-well-known package — may execute untrusted codeRUN npm install && npx tscFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Telegram Bot API URLtests/test_core.py:14 · Telegram Bot API URL — data will be sent to TelegramAPI = "https://api.telegram.org/bot{token}/sendMessage"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07

Cost to the agent

Instructions loaded
≈87 tok
1 file · 30 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 xonta-max-mcp@0.1.0 as of 54 min ago. This is the package itself, not its dependencies.

What would make this Verified

11 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim mrsergeiluzhnov: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  3. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  6. MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim mrsergeiluzhnovPropose a patch to the maintainer