Skip to content
View DonTrabajo's full-sized avatar
2 followers · 2 following

Block or report DonTrabajo

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
DonTrabajo/README.md

Don Trabajo

Offensive security tooling with OPSEC gates. Operational workflows stay private; public repos are sanitized and CI-gated.

Start here

  • ai-redteam-lab – Local-first adversarial test harness for LLMs: 33 cases across 8 attack categories, CI-enforced OPSEC gate
  • prox-recon – Offline-first recon core (linPEAS parsing + CVE matching) with CI-enforced OPSEC gates
  • ProxOffensive-AI-MultiAgent-Lab – Local-first multi-agent red-team lab: orchestration, LLM routing, and OPSEC-first workflows
  • apt33-scythe-case-study – APT33 emulation with detections, hunting queries, and tuning notes
  • recon-audit-sample – Sample external-exposure recon audit: methodology, report structure, and a full example report

What I build

  • AI-augmented recon and triage tooling
  • Multi-agent orchestration (local LLM → cloud fallback → none)
  • Emulation planning and detection engineering
  • Client-facing audit reports and methodology docs

Public vs private

Public repos contain demos, blueprints, and detection-focused writeups. Private repos contain operational workflows, lab bindings, and environment-specific automation. Reach out if you need deeper detail.

Contact

Principles

  • Reproducible results
  • Responsible disclosure
  • Measurable outcomes
  • Minimalism

Pinned Loading

  1. ai-redteam-lab ai-redteam-lab Public

    Local-first, reproducible adversarial test harness for evaluating LLM robustness — 50 cases across 10 attack categories, mapped to the Arcanum Prompt Injection Taxonomy, CI-enforced OPSEC gate.

    Python

  2. prox-recon prox-recon Public

    Prox Recon — offline-first recon core (linPEAS parsing + CVE matching) with CI-enforced OPSEC gates. Public core of Prox Offensive's recon tooling.

    Python

  3. ProxOffensive-AI-MultiAgent-Lab ProxOffensive-AI-MultiAgent-Lab Public

    Local-first multi-agent red-team lab — orchestration, LLM routing, and OPSEC-first workflows. Sanitized architecture + demos; operational state kept private.

    Python 1

  4. apt33-scythe-case-study apt33-scythe-case-study Public

    APT33 emulation case study with detections, hunting queries, and results/tuning notes.

    Python

  5. recon-audit-sample recon-audit-sample Public

    Sample external-exposure recon audit — methodology, report structure, and a full example report (public-safe).

    HTML