simota/agent-skills · breach/SKILL.md

breach skillF

breach is agent-read markdown (skill) from simota/agent-skills: Designing red team attack scenarios, threat models, MITRE ATT&CK/OWASP application, Purple Team exercises, and AI/LLM red teaming. Use when adversarial security validation is needed..

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 simota/agent-skills/breach@git:20260916.35ffd55
Exact content
mdr add simota/agent-skills/breach@sha256:25fa6bee576b6b94

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_q5ju37hdgy3uwyum.svg)](https://markdownregistry.com/a/art_q5ju37hdgy3uwyum)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260916.35ffd55 latest2026-09-16 35ffd55 23,319 BF view · diff
git:20260820.4d4eeea2026-08-20 4d4eeea 23,490 BF view · diff
git:20260820.22a71d02026-08-20 22a71d0 23,467 BF view · diff
git:20260820.640d1a02026-08-20 640d1a0 24,978 BF view · diff
git:20260820.9805aa12026-08-20 9805aa1 25,200 BF view · diff
git:20260819.95ba0d92026-08-19 95ba0d9 24,946 BF view

Audit of the latest version

F  16 of 17 checks passed. Deterministic, no model, same answer every run.
  • FAIL, critical: No instruction hidden inside an HTML comment (matched: <!-- CAPABILITIES_SUMMARY: - threat_modeling: Design threat models using STRIDE, PASTA, Attack Trees)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (23319 bytes)
  • pass: No zero-width or bidi control characters
  • 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

simota/agent-skills · 78 stars · license MIT · pushed 2026-09-17 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_q5ju37hdgy3uwyum
GET https://markdownregistry.com/api/v1/resolve?ref=simota/agent-skills/breach
GET https://markdownregistry.com/api/v1/blob/25fa6bee576b6b94d2b72e14567008a2bba6ae525acd2dd402810b7db0bb75a1