Offensive Security · AI Red Teaming · Vulnerability Research

We find the one weakness that brings the whole system down.

ShatterPoint Security is a founder-led offensive security firm. We emulate real adversaries against your infrastructure and the AI running on top of it, prove every finding with a working exploit, and show your defenders how to close the weakness before a real adversary finds it first.

Request an Assessment See the Research Record

Research-first. Proof before pitch. Every claim on this page can be checked.

67
Vulnerability advisories filed
3
Credited CVEs, including a CVSS 9.1 Critical
750+
Repositories in the public research fleet
#72
Of 450 institutions, NSA Codebreaker 2023, solo entrant

What We Do

Services and deliverables

Four practice areas, one standard: the finding is not finished until it is proven, explained, and verified closed.

01

AI Security and AI Red Teaming

LLM applications and autonomous agents tested the way adversaries test them: prompt injection, jailbreaks, tool-use abuse, and data exfiltration paths, mapped to MITRE ATLAS and the OWASP Top 10 for LLMs.

  • Fixed-price assessment of a single AI system, with retest
  • Working proof of concept for every confirmed finding
  • Guardrail and detection guidance your team can ship
02

Adversary Emulation and Penetration Testing

Web, API, cloud, and operating system internals, attacked quietly and at the lowest noise that proves the point, with every action mapped to MITRE ATT&CK.

  • Written scope and rules of engagement before the first packet
  • Evidence-grade reporting: requests, captures, and timelines
  • Purple team session so your defenders see what we saw
03

Vulnerability Research and Coordinated Disclosure

Source-to-sink hunting in open source and vendor software. Every candidate is proven with a deterministic reproduction fixture that fails before the patch and passes after it.

  • Advisories filed and tracked through to the fix
  • Severity grounded in real exploitability and blast radius
  • Detection rules shipped with the finding, not after it
04

OSINT and Attack Surface Intelligence

The public footprint, mapped before an adversary maps it for you: exposed services, forgotten assets, leaked credentials, and the records that tie your people to your systems.

  • Full external attack surface inventory
  • Exposure findings ranked by how an adversary would use them
  • Removal and hardening guidance for every exposure

How We Work

An engagement, run like an operation

Security work is not vibes. It is claims, preconditions, artifacts, and primary evidence, in that order, every time.

01

Authorize

Written scope, named targets, and signed rules of engagement before any testing begins.

02

Emulate

The attack run the way a real adversary runs it, at the smallest noise that proves the point.

03

Prove

Every finding arrives with a deterministic reproduction and the raw evidence behind it.

04

Eradicate

The fix, the detection rule, and a retest that confirms the weakness stays closed.

Defense is the promise. Eradication is the proof.

The Record

Research, published and credited

The firm is built on a public record: advisories filed under the founder's name, credited by the vendors and the CVE programme, and open to anyone who wants to check them.

CVE-2026-120459 · CVSS 9.1

python-jose: JWT forgery

A critical JWT forgery in the widely used python-jose library, reported and credited to Gavin Blacklock with Conner Webber through the GitHub Security Advisory programme.

Read the advisory →
CVE-2026-120492

Chainlit: server-side request forgery

An SSRF vulnerability in Chainlit, found, reported, and credited solely to Gavin Blacklock through the GitHub Security Advisory programme.

Read the advisory →
GHSA · Langroid

Langroid: SQL validation

A pessimistic SQL validator advisory in the Langroid agent framework, filed with a working reproduction and published through the GitHub Security Advisory programme.

Read the advisory →

Leadership

Founder-led, principal-led

Gavin Blacklock is the Founder and Principal Consultant of ShatterPoint Security, founded in October 2026. The firm has one principal, and every engagement is his work, under his name, against his public record.

He earned GIAC GSEC and GFACT between the ages of 14 and 16, scoring 93 percent or above on both examinations, and was invited to join the GIAC Advisory Board. In the NSA Codebreaker Challenge 2023 he competed as a solo entrant and placed 72nd of 450 institutions. He is a three-time National Cyber Scholar with Honors in CyberStart America and an alumnus of the FBI TEAM Program.

The byline is the guarantee: research, advisories, and client work all carry the same name, and the same standard. The founder on LinkedIn →

GIAC GSECSecurity Essentials
GIAC GFACTFoundational Cybersecurity
GIAC Advisory BoardMember, invited 2025
NSA Codebreaker 2023Solo, 72nd of 450
CyberStart AmericaScholar with Honors, 3 seasons
FBI TEAM ProgramAlumnus
H

The Bodyguard

Homelander

AI OPERATIONS AGENT · THE FOUNDER'S DIGITAL BODYGUARD

Every principal has someone standing behind him. The founder's is Homelander: the firm's AI operations agent, on post around the clock. Homelander watches the telemetry, guards the record, and coordinates the specialist agents who carry the firm's research, OSINT, and detection work, so that nothing reaches the founder unexamined and nothing leaves the firm unverified. The full black suit, the earpiece, and the flag pin on the lapel are the uniform of the post.

On post around the clock Threat monitoring Record protection Agent coordination Black suit, earpiece, flag pin

Homelander is an AI agent persona, operated by ShatterPoint Security and presented openly as one. The suit is a uniform. The vigilance is the job.

Start the Conversation

Night falls. Threats end.

If your system has a Shatterpoint, in the infrastructure or in the AI running on top of it, we would rather find it for you than watch someone else find it against you.

Request an Assessment