I'm Hala Naaz, a cybersecurity learner and security-tool builder focused on AI Security, AI Red Teaming, and Security Research. I learn by building practical projects, testing ideas in controlled environments, documenting findings, and exploring how AI applications and agents can fail in unexpected ways.

Through AshlynxCyber, I share my projects, research, and hands-on cybersecurity work.

• LLM Security: prompt injection, adversarial testing, and AI application attack surfaces
• AI Agent Security: tool access, privilege boundaries, intent alignment, and safe agent behaviour
• RAG Security: risks around retrieval pipelines, untrusted content, and data handling
• Security Research: threat modelling, controlled experiments, reproducible findings, and mitigations
• Hands-on Practice: TryHackMe, CTFs, home labs, and security tool development

Additional work: Ransomware Detection & Response System · Healysis

AI Security · Offensive Security · Security Research · Defensive Security

Focus areas

• LLM and AI application security
• AI red teaming and adversarial testing
• Prompt injection and jailbreak testing
• AI agent security and tool-use boundaries
• Retrieval-Augmented Generation (RAG) security

Research themes: threat modelling · attack-surface analysis · security evaluation · mitigation strategies

Tool	Purpose / practice area
Nmap	Network discovery and service enumeration
Burp Suite	Web application testing and HTTP request analysis
Metasploit	Exploit validation in authorised labs
Shodan	Internet-facing asset and service reconnaissance
Recon-ng	OSINT and reconnaissance workflows

Practice areas: web security testing · network reconnaissance · vulnerability assessment · CTFs · authorised lab testing

Logo	Platform / tool	Use
	Kali Linux	Security testing workstation
Parrot OS	Parrot OS	Security-focused Linux environment
	Windows	Primary desktop environment
	Google Antigravity IDE	AI-assisted development workflow
	Visual Studio Code	Code editing and project development
	Git	Version control
	GitHub	Source control and project documentation

Logo	Platform	Learning / practice focus
	Splunk	Log search, SPL queries, dashboards, alerts, and security-event investigation
	Elastic	Log analytics and observability concepts

Splunk — current learning focus

• Searching and analysing logs, machine data, and security events
• Practising SPL (Search Processing Language) queries
• Exploring dashboards, alerts, and detection workflows
• Learning how SIEM workflows support threat hunting and incident investigation

Logo	Language	Application
	Python	Security scripts, automation, and application logic
	Bash	Shell scripting and command-line automation

Logo	Technology	Application
	FastAPI	Python API development
Next.js	Next.js	Web application development
	TypeScript	Frontend and application development
	AWS	Cloud services and serverless project work
	Docker	Containerisation and local development
	PostgreSQL	Relational data storage

_{Capability note: this section combines hands-on project work, authorised lab practice, and ongoing learning. Tools are listed to show the working toolkit—not to imply expert-level proficiency in every platform.}

• TryHackMe & CTFs — practising security concepts in authorized lab environments
• AI Security Research — documenting research questions, experiment designs, observations, and mitigations
• Project Development — building and improving cybersecurity and AI-related tools
• Technical Writing — maintaining project documentation, research notes, and lab write-ups