At Freelance, I test production targets through HackerOne, Bugcrowd, and Intigriti. I chained SSRF in a document export feature to file access through an exposed Chrome DevTools Protocol socket, recovering production database credentials.
I also investigate AI assistant security, including system prompt extraction, indirect prompt injection, and markdown-based data exfiltration. I publish working exploits on GitHub and technical write-ups at cubit.blog, and bring hands-on experience in Active Directory testing and defensive security.

