Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Self-Hosted LLM Config Check

    1

    This skill finds those and nine other self-hosted LLM mistakes before you expose the server, and tells you how to fix each one.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Self-Hosted LLM Config Check

    Example session with this skill installed

    Check this project with self-hosted-llm-config-check.

    • Read your context and instructions
    • Compiled the self-hosted llm config

    $ python3 scripts/check_llm_server.py examples/risky
    BLOCK compose.yaml:7 L01 INFERENCE_API_OPEN_TO_NETWORK
    - "11434:11434"
    Why: An Ollama, vLLM, llama.cpp server, LocalAI, Text Generation Inference or LiteLLM proxy endpoint is reachable beyond this machine (a Compose port without 127.0.0.1, network_mode: host, a LoadBalancer or NodePort Service, hostNetwork, or a 0.0.0.0 bind) and no API key is set. Anyone who can reach the port can run your models on your GPUs, read what they return and, on Ollama, pull and delete models. Ollama has no API key setting at all.
    Safer: Publish the port on 127.0.0.1 only ("127.0.0.1:11434:11434") or not at all, and let other containers reach it over the Compose network. Ollama has no API key setting: if other machines must call it, put an authenticating reverse proxy in front.

    BLOCK compose.yaml:20 L02 SECRET_IN_CONFIG
    BLOCK compose.yaml:31 L03 WEBUI_AUTH_OFF_ON_NETWORK
    BLOCK deploy/llama-server.service:8 L01 INFERENCE_API_OPEN_TO_NETWORK
    BLOCK litellm/config.yaml:10 L02 SECRET_IN_CONFIG
    BLOCK production.env:4 L04 NEW_USERS_BECOME_ADMIN
    REVIEW Dockerfile:1 L14 MOVING_IMAGE_TAG
    REVIEW compose.yaml:5 L14 MOVING_IMAGE_TAG
    REVIEW compose.yaml:9 L12 ANY_BROWSER_ORIGIN_ALLOWED
    REVIEW compose.yaml:15 L12 ANY_BROWSER_ORIGIN_ALLOWED
    REVIEW compose.yaml:17 L11 TRUST_REMOTE_CODE
    REVIEW compose.yaml:21 L16 RISKY_SERVER_OPTION
    REVIEW compose.yaml:23 L15 PUBLIC_PORT_WITHOUT_TLS
    REVIEW deploy/llama-server.service:8 L16 RISKY_SERVER_OPTION
    REVIEW k8s/open-webui.yaml:7 L13 NEW_ACCOUNTS_NOT_APPROVED
    REVIEW k8s/open-webui.yaml:25 L14 MOVING_IMAGE_TAG
    REVIEW k8s/open-webui.yaml:37 L15 PUBLIC_PORT_WITHOUT_TLS
    REVIEW litellm/config.yaml:13 L17 WEAK_OR_EXAMPLE_SECRET
    REVIEW production.env:5 L17 WEAK_OR_EXAMPLE_SECRET

    (Each finding also has Why and Safer lines, as in the first one.)
    Verdict: BLOCK. Checked 6 files, 6 with LLM server config content.
    This is a static check of file text. NOT FLAGGED is not a guarantee.

    BLOCK compose.yaml

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Publishing port 11434:11434 on the official Ollama image puts an API with no password on every network interface of your GPU server, and WEBUI_AUTH=False on a published Open WebUI makes every visitor an administrator who can run Python on the server. This skill finds those and nine other self-hosted LLM mistakes before you expose the server, and tells you how to fix each one.

    Your agent runs a scanner on your Compose files, Kubernetes manifests, Dockerfiles, systemd units and drop-ins, .env files and LiteLLM proxy configs. It recognises each server by its image or command and knows its defaults: the official Ollama and llama.cpp images listen on all interfaces, ollama serve and llama-server on a bare host listen on 127.0.0.1, and vLLM, LocalAI, TGI and the LiteLLM proxy listen on all interfaces unless told otherwise. A port published on 127.0.0.1, a bind to one LAN or VPN address and an internal cloud load balancer are not reported; settings a container takes from a ConfigMap in the same manifest count as its own; ${VAR}, secretKeyRef and LiteLLM environment references count as references, and dummy keys such as fake-key or EMPTY for a backend that needs none are not secrets. Each open-port finding names that server's own port, bind setting and key setting. It never starts a server, a container or a model. It returns BLOCK, REVIEW, or NOT FLAGGED, with the file, line, reason, and a safer approach. Secrets are never printed.

    What it checks

    BLOCK

    • L01: an Ollama, vLLM, llama.cpp server, LocalAI, TGI or LiteLLM proxy reachable from the network (published port, host network, LoadBalancer or NodePort Service, 0.0.0.0 bind) with no API key
    • L02: API keys (including key lists such as OPENAI_API_KEYS), master keys, tokens and passwords written in Compose, Kubernetes, Dockerfile, systemd or LiteLLM config files or on the command line
    • L03: Open WebUI with WEBUI_AUTH turned off and reachable from the network
    • L04: Open WebUI DEFAULT_USER_ROLE=admin while sign-up, OAuth sign-up, LDAP or header login can create accounts

    REVIEW

    • L11: --trust-remote-code without a revision pinned to a commit
    • L12: * in OLLAMA_ORIGINS, vLLM --allowed-origins and other CORS settings, and vLLM releases before 0.32.0 whose default allowed any origin
    • L13: Open WebUI sign-up without approval (role user), or admin as the default role
    • L14: model server images with no version in the tag (latest, main, server-cuda)
    • L15: API or UI ports published over plain HTTP, including vLLM paths its --api-key does not cover
    • L16: vLLM dev mode, insecure serialization or wide local media access, and llama-server --props
    • L17: keys and passwords set to sample or default values from the docs, or a dummy value used as a server's own key

    What's included

    • The scanner (Python 3.9+, standard library only)
    • A rules guide with the reason, safer approach and official documentation link for each rule
    • A risky and a safe example project, and the real report the scanner produces on the risky one

    Limits It reads each file on its own: a Service, ConfigMap or .env file kept in another file is not joined to its server, and docker run commands in scripts are not read. Firewalls, cloud security groups and reverse proxies configured elsewhere are not seen, and Open WebUI settings changed in its admin panel are not checked. SGLang, TabbyAPI and LM Studio are not covered. The Ollama and llama.cpp quick-start port mappings are reported on purpose, because they publish an API without a key on every interface. NOT FLAGGED is not a guarantee.

    Static check of config text. Firewalls, proxies in other files and settings changed in the Open WebUI admin panel are not seen. NOT FLAGGED is not a guarantee.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 4 days ago

    Permissions

    Terminal / Shell
    Read Files

    Runs one local Python script in the terminal. It reads your project's files, writes nothing, and makes no network calls. The example project includes clearly fake, inert keys (NOTREAL...) and the public sample master key from the LiteLLM docs for the scanner to find. Nothing is started.

    Listed4 days ago

    What's inside

    Frequently Asked Questions

    No. The script reads local files only and makes no network calls.

    No. It only reports. Your agent changes files only if you ask it to.

    Any agent that supports SKILL.md skills and can run a terminal command, such as Claude Code. It needs Python 3.9 or newer and nothing else.

    No. It reads your Compose, Kubernetes, systemd and LiteLLM files as text. It never calls Ollama, vLLM or any other server, and never pulls an image.

    BLOCK: fix it before you ship. REVIEW: check it before release. NOT FLAGGED: no rule matched. It is a static check, so NOT FLAGGED is not a guarantee.

    New in Security