jailbreak bug-bounty vulnerability ai-safety memory-injection claude responsible-disclosure security-research red-teaming ai-security prompt-injection anthropic llm-security constitutional-ai character-drift

jailbreak bug-bounty vulnerability infosec ai-safety hackerone memory-injection claude responsible-disclosure security-research red-teaming ai-security ai-alignment prompt-injection anthropic llm-security constitutional-ai claude-code model-safety character-drift