> SYS_INIT: AUTHORIZED
> USER: fabian@crespo
> ROLE: PRINCIPAL_PENETRATION_TESTER
> STATUS: ONLINE — AVAILABLE_FOR_ENGAGEMENTS

Fabian
CRESPO_

Principal Penetration Tester — 4+ years of offensive security operations across network, application, AI/ML, and cloud assessments. Adversarial testing for healthcare, finance, and tech.

~270 Engagements
280+ Findings Produced
15 Certifications
>_EXECUTE_EXPERIENCE >_SAMPLE_REPORTS
// whoami

The operator.自己

Hello—welcome to the portfolio. I started my penetration testing journey in the fall of 2021 with no prior hacking experience, aiming to break into the field within a year. After grinding offensive security labs and stacking certifications, I landed a role shortly after earning the OSCP.

I am now an offensive security professional with 4+ years of experience spanning network, application, AI/ML, and cloud penetration testing.

I conduct adversarial assessments against generative and predictive AI systems — including prompt injection, indirect prompt injection through agentic pipelines and RAG architectures, and model inference attacks — alongside traditional application and infrastructure engagements.

Outside of work, I train regularly at the gym and compete in combat sports — I hold a blue belt in Brazilian Jiu-Jitsu. When I’m not on the mats, I unwind with anime and video games. My most recent obsession is the Resident Evil series.

// Core Disciplines
AI/ML Pentesting Prompt Injection RAG & Agentic Attacks Web Application Cloud (AWS · Azure · GCP) Active Directory Red Team Ops Malware Dev Essentials
// ls -la ~/projects

Selected projects.作品

[ AI Projects ] 05 entries
// 01
APE-Taxonomy-Analysis

Maps 56 adversarial AI challenges across 10 platforms to HiddenLayer’s APE Taxonomy by objective, tactic, and technique. Includes full prompts, model responses, and defensive countermeasures.

Markdown / Research
// 02
spam-classifier

SMS Spam Classifier built with TF-IDF and Naive Bayes as part of the HTB Academy AI in InfoSec track. Explores ML model behavior and misclassification attack surfaces in a security context.

Python
// 03
Secure Code Games: Agentic AI

Deployment and write-up of GitHub’s Secure Code Game on Agentic AI Security. Covers securing AI agents that execute commands, browse the web, use tools, and coordinate other agents.

JavaScript
// 04
mcpfox

MCP Server Security Analysis Tool — built for assessing the security posture of Model Context Protocol servers, a key attack surface in agentic AI deployments.

Python
// 05
HexProbe

Browser-based red-teaming workbench for LLM applications. Ships a curated library of 137+ attack prompts and supports live endpoint probing, determinism analysis, structured test logging with AI-assisted evaluation, and exploit-chain visualization — all client-side with no backend.

TypeScript
[ Cloud Tools ] 04 entries
// 06
azure_collect

Modular Azure / Entra ID collection and tool orchestration scripts for cloud penetration testing. Automates enumeration of identities, roles, and permissions across Azure tenants.

Python
// 07
AWS-Exploitation-Tooling

Scripts for exploiting AWS services — built for ARTE labs covering IAM abuse, privilege escalation, storage enumeration, and cross-account trust exploitation.

Python
// 08
CloudFox-Command-Runner

Automation script for running CloudFox commands during AWS penetration tests. Streamlines cloud enumeration workflows and produces organized output for reporting.

Python
// 09
Sirocco

PowerShell password-spraying tool for Microsoft Online (Azure / Entra ID / Office 365) that routes every authentication attempt through a FireProx API Gateway endpoint, rotating the source IP per request.

PowerShell
[ Web Application Tools ] 03 entries
// 10
URL-Importer

Burp Suite extension for bulk URL importing. Streamlines web application testing by automating request importing into the Burp proxy — eliminates tedious manual entry during large-scope assessments.

Python
// 11
pySpider

Tool for harvesting JavaScript files from web applications for endpoint discovery and attack surface mapping. Accelerates manual JS analysis during web application penetration tests.

Python
// 12
AgentE

Orchestration tool designed to facilitate the reconnaissance process during web application penetration tests. Streamlines and automates information-gathering workflows.

Python
[ AD / Network Tools ] 01 entry
// 13
Brenmon

Port of Invoke-ADEnum in Python using impacket and ldap3. Enumerates Active Directory environments with HTML report generation and JSON export — built for operator efficiency during internal network assessments.

Python
// cat experience.json

Field operations.経験

Principal Penetration Tester
Clearwater Security
Oct 2022 — Present
  • Delivered ~270 penetration testing engagements across healthcare, finance, and technology sectors — spanning internal, external, assumed-breach, web application, AI/ML, and cloud assessments. Produced over 280 findings, accounting for 20% of all findings and 30% of all critical issues identified across the team’s portfolio.
  • Conducted AI/ML penetration tests against generative and predictive systems. Executed adversarial attacks encompassing jailbreaks, instruction hierarchy bypass, indirect prompt injection through agentic pipelines and RAG architectures, and model inference attacks against LLM-integrated production applications built on platforms such as Vertex AI.
  • Assessed multi-modal AI systems, applying image-based prompt injection and steganographic payload embedding to probe vision-language model attack surfaces. Identified and validated CVE exploitation within AI-integrated document processing pipelines, establishing end-to-end attack chains from crafted document ingestion through renderer exploitation to arbitrary JavaScript execution.
  • Developed a structured adversarial AI testing methodology mapped to HiddenLayer’s APE taxonomy, classifying attack chains by objective, tactic, and technique across task redirection and safety control bypass objectives. Applied direct prompt injection, system prompt extraction, refusal suppression, jailbreak chaining, and steganographic payload embedding against deployed AI systems.
  • Conducted web application security assessments targeting REST and GraphQL APIs, SPA frameworks, and legacy application servers. Exploited injection flaws, broken object-level and function-level access controls, SSRF, and session management weaknesses. Achieved first-place recognition in a competitive timed assessment identifying critical XSS, SQLi, IDOR, and authentication bypass vulnerabilities.
  • Conducted cloud penetration tests across AWS, Azure, and GCP, exploiting misconfigured IAM roles, over-privileged service accounts, publicly exposed storage, and insecure cross-account trust relationships. Escalated from initial access to full tenant or account compromise across multiple client engagements.
  • Executed internal network and Active Directory penetration tests across hundreds of enterprise Windows environments, delivering full kill-chain compromises including protocol poisoning, service enumeration and exploitation, and abuse of insecure object permissions.
// grep -r "certified" ~/achievements

Stacked credentials.認証

Practical AI Pentest Associate
PAPA · TCM Security
Verify
Certified AI Security Expert
MSec-CAIS · Modern Security
View Certificate
HTB Certified Offensive AI Expert
COAE · HackTheBox
View Certificate
AI/ML Pentester
C-AI/MLPen · SecOps Group
View Certificate
Experienced Penetration Tester
OSEP · Offensive Security
Verify
Certified Penetration Tester
OSCP · Offensive Security
Verify
Certified Red Team Operator
CRTO · Zero-Point Security
Verify
Red Team Operator: Windows Evasion
Sektor7 · Red Team Operator
View Certificate
Red Team Operator: Malware Dev Essentials
Sektor7 · Red Team Operator
View Certificate
Azure Red Team Professional
CARTP · Altered Security
View Certificate
AWS Red Team Expert
ARTE · HackTricks
Verify
Offensive AWS Security Professional
OAWSP · Pwned Labs
Verify
GCP Red Team Expert
GRTE · HackTricks
Verify
Certified Professional Penetration Tester
eCPPT · INE Security
Verify
Junior Penetration Tester
eJPT · INE Security
Verify
// cat publications.md

Writing & research.研究

Methodology
Penetration Testing Methodology Wiki

Comprehensive penetration testing wiki covering enumeration, exploitation, privilege escalation, post-exploitation, and Active Directory attack chains. Structured as a practitioner reference for real engagements and CTF challenges.

Enumeration Exploitation PrivEsc Post-Exploitation Active Directory
Walkthrough
APE Taxonomy: Adversarial AI Analysis

Detailed analysis mapping 56 adversarial AI challenges across 10 platforms to HiddenLayer’s APE Taxonomy. Includes full attack prompts, model responses, bypass techniques, and defensive countermeasures for each challenge.

Prompt Injection Jailbreaking LLM Security APE Taxonomy
// ls -la ~/reports

Sample reports.報告

The following sanitized report demonstrates the depth and quality of findings produced during penetration testing engagements. Provided for recruiter and hiring manager review.

// AI Penetration Test
AI Application Penetration Test Report
Prometheon HTB AI Lab  ·  HackTheBox AI Security Assessment
Download PDF
AI/ML Security Prompt Injection LLM Exploitation HackTheBox Adversarial AI APE Taxonomy