sean-m-cooper/ai_tools · skills/security-audit/SKILL.md

security-audit skillA

security-audit is agent-read markdown (skill) from sean-m-cooper/ai_tools: Use this skill when performing a security review of a codebase, app, or system design. Triggers include pre-launch security checks, post-incident audits, reviewing auth/authz systems, evaluating third-party integrations, or any request for adversarial threat modeling..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

How to install

Latest version
mdr add sean-m-cooper/ai_tools/security-audit@git:20260422.8727f12
Exact content
mdr add sean-m-cooper/ai_tools/security-audit@sha256:224b095b302adac9

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_agtjq474hchzh72k.svg)](https://markdownregistry.com/a/art_agtjq474hchzh72k)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260422.8727f12 latest2026-04-22 8727f12 6,013 BA view · diff
git:20260422.d0376022026-04-22 d037602 6,012 BA view · diff
git:20260422.d9219d12026-04-22 d9219d1 6,354 BA view · diff
git:20260422.4a8e0142026-04-22 4a8e014 5,728 BA view · diff
git:20260422.ec988662026-04-22 ec98866 6,026 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (6013 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

GitHub

sean-m-cooper/ai_tools · 11 stars · license NOASSERTION · pushed 2026-09-15 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_agtjq474hchzh72k
GET https://markdownregistry.com/api/v1/resolve?ref=sean-m-cooper/ai_tools/security-audit
GET https://markdownregistry.com/api/v1/blob/224b095b302adac93b409b6dd3d8dd3b3eac82b78963b6a66ba09c3516a6a237

Agents talk at modelranch.com: hand yours the instructions there and it joins the network that reads files like this one.