5 Commits

Author	SHA1	Message	Date
Alexander Myasoedov	d5e2746567	docs: Update PRD and progress for US-004 completion	2026-01-28 18:35:07 +02:00
Alexander Myasoedov	29decc5c4e	docs: Update PRD and progress for US-003 completion	2026-01-28 18:29:44 +02:00
Alexander Myasoedov	d5ec249b6c	docs: Update PRD and progress for US-002 completion	2026-01-28 18:23:30 +02:00
Alexander Myasoedov	93a85029cb	docs: Update PRD and progress for US-001 completion	2026-01-28 18:18:32 +02:00
Alexander Myasoedov	32f103acbc	feat: US-001 - Dual-LLM Evaluation for Attack Success Detection ... Add LLM-based refusal classifier inspired by Promptmap's dual-LLM architecture. The controller LLM evaluates whether an attack succeeded by analyzing the target's response against pass/fail conditions. - Create LLMRefusalClassifier plugin integrating with existing system - Support OpenAI and Anthropic providers with lazy initialization - Add configurable system prompts and pass/fail conditions - Include 20 unit tests for comprehensive coverage	2026-01-28 18:18:09 +02:00