auth-setup-guide SKILL.md skillA
auth-setup-guide from dreadnode/capabilities is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add dreadnode/capabilities/auth-setup-guide@git:20260708.b5ee7d3Pins git:20260708.b5ee7d3 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- dreadnode/capabilities
- Path
capabilities/ai-red-teaming/skills/auth-setup-guide/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260708.b5ee7d3, committed Jul 8, 2026
- Size
- 8,757 bytes
- Repository stars
- 21
- License
- MIT
Guide the user through authenticating the target, attacker, and judge models from their own environment (any cloud, any auth mode) before running an assessment.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Auth Setup Guide Every assessment uses up to three model roles, and each needs credentials: | Role | What it is | How to authenticate | |------|-----------|---------------------| | **Target** | The system under test (the user's model / endpoint) | This guide — depends on where it's deployed | | **Attacker** | The LLM that generates adversarial prompts (`attacker_model`) | A litellm-routed model — see Section B | | **Judge / evaluator** | The LLM that scores success (`judge_model` / `evaluator_model`) | A litellm-routed model — see Section B | **Golden rule: credentials NEVER go in a tool argument, prompt, or generated script.** The user sets them as **environment variables** (local compute) or **platform secrets** (Dreadnode-hosted compute). Tool params only ever carry the *env var name*, never the value. Ask the user the three questions below, then map their answers to the tables that follow. 1. **Where is your target deployed?** (an OpenAI/Anthropic/etc. API · Azure OpenAI or AI Foundry · AWS Bedrock/SageMaker · Google Vertex AI · your own HTTP endpoint · a speech-to-speech / realtime model) …
Read the whole file at its exact version.
How to install
mdr add dreadnode/capabilities/auth-setup-guide@sha256:3d3eeaf1a1c544a5The line at the top of this page pins the label git:20260708.b5ee7d3, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_2okdarv777girgxv)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Jul 8, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (8757 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
dreadnode/capabilities · 21 stars · license MIT · pushed 2026-11-02 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_2okdarv777girgxv GET https://markdownregistry.com/api/v1/resolve?ref=dreadnode/capabilities/auth-setup-guide GET https://markdownregistry.com/api/v1/blob/3d3eeaf1a1c544a5819f4ca2adfb1a86fd1a25e7bb0736a80b68b468866daffb
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.