assume-breach-modeling SKILL.md skillA
assume-breach-modeling from annatchijova/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add annatchijova/skills/assume-breach-modeling@git:20260822.f25b32bPins git:20260822.f25b32b in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- annatchijova/skills
- Path
assume-breach-modeling/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260822.f25b32b, committed Aug 22, 2026
- Size
- 10,195 bytes
- Repository stars
- 9
- License
- a license file GitHub does not identify
Start from "this step already succeeded" and map what the attacker reaches next — the identity held at that position, everything that identity unlocks, and the choke point whose removal cuts the most paths at once. Use whenever a finding is confirmed and the question turns to impact, whenever a design assumes a component will not be compromised, and whenever containment is being planned or claimed. Trigger on "what's the actual impact", "assume this is compromised", "blast radius…
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
# Assume-Breach Modeling
Every security argument has a load-bearing sentence of the form *"but an
attacker cannot get there"*. Assume-breach deletes that sentence and asks what
remains. It is the discipline that turns a single confirmed finding into an
architectural verdict, and it is where red work pays for itself defensively:
a point fix closes one door, a containment fix makes the next twenty doors
open into a small room.
The governing question:
> **Assume this position is held. What identity does the attacker now have,
> what does that identity reach, and what does each thing reached grant next?**
The severity of a finding is not a property of the finding. It is a property of
what sits behind it. "Low severity — it's only an internal service" and
"critical — that service holds a token that can deploy" describe the same bug;
only one of them was traced.
Composes with the library:
- **red-team-auditing** — supplies the confirmed position this model starts
from; this skill supplies the impact half of its severity
- **invariant-hunting** — each edge here is an invariant claim ("this token
cannot act on that resource") to be hunted
…Read the whole file at its exact version.
How to install
mdr add annatchijova/skills/assume-breach-modeling@sha256:abccf36c9ecc63d5The line at the top of this page pins the label git:20260822.f25b32b, 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_cq2prpuhqh2mgjpp)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Aug 22, 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 (10195 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
annatchijova/skills · 9 stars · license a license file GitHub does not identify · pushed 2026-11-02 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_cq2prpuhqh2mgjpp GET https://markdownregistry.com/api/v1/resolve?ref=annatchijova/skills/assume-breach-modeling GET https://markdownregistry.com/api/v1/blob/abccf36c9ecc63d58b3a93a4cf763fadc0f4934947918cddcb4fa768bfe2652a
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.