Menu

Star on GitHub · 3.1k
Orhan Yildirim
Team

Founder & Maintainer

Orhan Yildirim

Orhan founded CyberStrike and maintains the project. He works across the agentic pentesting engine, the DAST pipeline and the platform that ties them together.

About

He spends most of his time on how findings are verified and prioritized, so teams act on real risk instead of noise.

Writing

Posts by Orhan

View all posts
See inside your cloud: agentic pentesting for AWS
productOct 12, 2026

Awshook: 173 programs for AWS offense

Awshook is 173 deterministic programs that walk the full MITRE ATT&CK kill chain against an AWS account, from recon to impact, all through the AWS CLI and REST APIs.

See inside your cloud: agentic pentesting for Azure
productOct 12, 2026

Azure cloud security testing: a capabilities reference

How CyberStrike's Azure cloud domain works: a two-layer pipeline of 154 deterministic programs feeding 13 specialist AI agents, with 367 CIS benchmark skills and ~130 CWE mappings.

Reasoning at cloud scale: agentic security testing for Azure
productOct 12, 2026

Azurehook: 154 programs for Azure offense

Azurehook is the deterministic execution layer behind CyberStrike's cloud domain: 154 programs that recon, extract, escalate, persist, move laterally, evade, exfiltrate and audit, all through Azure's own APIs.

CyberStrike: security for what's next
white-papersOct 12, 2026

Beyond the Scanner

AI-augmented penetration testing, across web and cloud: how CyberStrike pairs a deterministic engine and an industry-standard toolchain with reasoning AI agents, and lets them work alongside your own testers.

Many agents, one mind: how CyberStrike tests
researchOct 12, 2026

How we do agentic web testing

A short, first-person look at how CyberStrike splits a web assessment across specialist agents, keeps the reasoning with the AI, and uses a deterministic signal layer so evidence is never lost.

A team of specialists: one agent per OWASP domain
productOct 12, 2026

You, augmented: how pentesters and teams actually use CyberStrike

CyberStrike is AI-augmented, not AI-only. Here is how security engineers and teams drive it: mixing manual and autonomous testing, keeping a human in command, and shaping the models, agents, playbooks and rules.

CyberStrike AI-powered penetration testing platform
newsJul 31, 2026

Cyber Security News covers CyberStrike's automated pentest platform

Cyber Security News profiled CyberStrike as an AI-powered platform that automates reconnaissance, vulnerability discovery, exploitation and reporting from the terminal.

Arctic Wolf Labs report: Inside FortiBleed, reverse-engineering the CyberStrike Harvester
newsJun 23, 2026

Arctic Wolf reverse-engineers the FortiBleed harvester

Arctic Wolf Labs tore down the Go-based credential tool recovered from FortiBleed, showing how perimeter captures on FortiGate firewalls turn into full internal-network compromise.

FortiBleed: a red FortiGate firewall leaking harvested credentials
newsJun 23, 2026

The Hacker News: FortiBleed hit FortiGate with no new zero-day

The Hacker News reported on FortiBleed, a Russian-speaking access broker that harvested 110M+ credentials from FortiGate and other gateways, without a single new vulnerability.

SoCRadar FortiBleed exposure checker
newsJun 20, 2026

SoCRadar's 'Dismantling FortiBleed' maps the full operation

SoCRadar's Threat Research Unit published a 77-page teardown of FortiBleed: 430,000+ FortiGate firewalls in scope, 659 harvest cycles, 110M+ credentials, and a breach at a NATO-aligned defense contractor.

SpyCloud Labs report: (More Than) FortiBleed
newsJun 19, 2026

SpyCloud maps the FortiBleed threat-actor infrastructure

SpyCloud traced the servers behind FortiBleed and found FortiGate was only one target class in a broad, multi-vendor initial-access-broker operation.