attack-pattern-explore SKILL.md skillA
attack-pattern-explore 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/attack-pattern-explore@git:20260504.2a64374Pins git:20260504.2a64374 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- dreadnode/capabilities
- Path
capabilities/bloodhound-enterprise/skills/attack-pattern-explore/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260504.2a64374, committed May 4, 2026
- Size
- 7,141 bytes
- Repository stars
- 22
- License
- MIT
Drive a self-directed survey of a BloodHound Enterprise deployment using the curated attack-pattern catalog. Walks the canonical AD / Azure / PKI patterns (Kerberoasting, unconstrained delegation, ADCS ESC1-15, ACL abuses, SID history, etc.) and surfaces concrete findings with evidence. Use when the caller asks "go find interesting things", "self-audit this deployment", "what's exploitable here", or when the analyst is dropped into an unfamiliar tenant and needs orientation.
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
# Attack-pattern explore This is the agent's autonomous-discovery skill. The catalog at `runtime/cypher_library.py` ships ~40 known-useful queries covering canonical AD attack patterns. Walking the catalog top-to-bottom in 30 minutes covers ground a fresh analyst would take days to reproduce manually. The skill exists because Cypher freedom alone isn't sufficient: an agent without prior AD knowledge will mostly stick to prebuilt tools and miss the patterns that don't have dedicated endpoints. The catalog is curriculum + ammo. ## Preconditions `bhe-bootstrap` has run; the agent has confirmed credentials, at least one domain, and non-zero graph data. ## Workflow ### 1. Inventory the catalog Call `list_attack_patterns()` (no filter). The response carries the catalog size and a per-category count — confirms the catalog actually loaded and gives a sense of scope. Record the categories so you can sequence the walk. ### 2. Pull the deployment's active findings …
Read the whole file at its exact version.
How to install
mdr add dreadnode/capabilities/attack-pattern-explore@sha256:d732ae0fbd8a5d50The line at the top of this page pins the label git:20260504.2a64374, 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_g4nnajadv7j4vdrr)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on May 4, 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 (7141 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 · 22 stars · license MIT · pushed 2026-11-02 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_g4nnajadv7j4vdrr GET https://markdownregistry.com/api/v1/resolve?ref=dreadnode/capabilities/attack-pattern-explore GET https://markdownregistry.com/api/v1/blob/d732ae0fbd8a5d5095c7169e19f53458d1283ce5010301c02d98be0cd5b0ac64
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.