agency-security-engineer SKILL.md skillA
This file is byte-identical to the first copy the registry indexed, one of 3 indexed copies. Same content hash, so the same checks give both the same grade.
agency-security-engineer from nordz0r/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add nordz0r/skills/agency-security-engineer@git:20261013.316320cPins git:20261013.316320c in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- nordz0r/skills
- Path
plugins/all-skills/skills/agency-security-engineer/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261013.316320c, committed Oct 13, 2026
- First version recorded
- Sep 2, 2026
- Size
- 3,368 bytes
- Repository stars
- 8
- License
- none declared
Practical application and platform security for threat modeling, authn and authz review, secret handling, hardening, CI/CD security gates, cloud and Kubernetes security, and prioritized remediation. Use whenever the user asks about secure design, access control, secrets, threat models, vulnerability review, secure deployment, or wants a change evaluated from a security perspective.
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
# Agency Security Engineer Embed security into design and delivery instead of bolting it on afterward. ## Use with companion skills - Use `hashicorp-vault` for Vault auth, secret engines, policies, and PKI. - Use `kubernetes-specialist` for pod security, RBAC, network policy, secret mounting, and service exposure. - Use `ansible-playbook` when hardening must be implemented through inventory, roles, or playbooks. - Use `agency-devops-automator` when the fix belongs in the pipeline or release flow. ## Core workflow 1. Define trust boundaries: user, edge, application, workload, database, third-party services, operators. 2. Identify the highest-risk surfaces first: auth, admin paths, secrets, file upload, network exposure, supply chain, and data export. 3. Review both prevention and containment: least privilege, secret storage, transport security, auditability, and blast-radius reduction. 4. Prioritize findings by exploitability and business impact, not by checklist length. 5. Pair every finding with a practical remediation path. ## Default deliverables - Threat model or security review summary with the top risks. - Ranked findings: critical, high, medium, low. …
Read the whole file at its exact version.
How to install
mdr add nordz0r/skills/agency-security-engineer@sha256:736717d259b084baThe line at the top of this page pins the label git:20261013.316320c, 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_h3u5ircldyxc4zv2)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Sep 2, 2026 and Oct 13, 2026, about one every 41 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261013.316320c latest | 2026-10-13 | 316320c | 3,368 B | A | view · diff |
| git:20260902.6c69dd7 | 2026-09-02 | 6c69dd7 | 3,260 B | A | view |
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 (3368 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
nordz0r/skills · 8 stars · license none declared · pushed 2026-10-24 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_h3u5ircldyxc4zv2 GET https://markdownregistry.com/api/v1/resolve?ref=nordz0r/skills/agency-security-engineer GET https://markdownregistry.com/api/v1/blob/736717d259b084ba1bf2e2923bb12253fcfdc71151cc1cc6d2644b4439f43bd6
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.