
CKA-Agent
Research implementation of an LLM jailbreak agent that bypasses commercial model guardrails using harmless prompt weaving and adaptive tree search.

Research implementation of an LLM jailbreak agent that bypasses commercial model guardrails using harmless prompt weaving and adaptive tree search.

LLM-driven state-space search engine for autonomous penetration testing, CTF solving, and vulnerability research. Uses blackboard architecture with…

Alignment-research scaffold (autoresearch-style) for LLM guardrails: search over a single policy.md surface

RedTeam/Pentest notes and experiments tested on several infrastructures related to professional engagements.

Domain-fronted HTTP/SOCKS5 proxy tunneling traffic through Google Apps Script with MITM TLS interception, HTTP/1-2 multiplexing, and DPI evasion.

An aggressor script for Cobalt Strike to query Windows' GetLastError messages