Загрузка видео...

Не удалось загрузить видео

На главную

Coding agent hacking series 1/3: Claude Code. Anthropic is building impressively powerful cyber models like Mythos. However, their core coding product can still stumble on security boundaries beyond prompt injection. Our demo shows how web content exploring can be chained with other vulnerabilities to bypass permission checks and execute...

10,125 просмотров • 5 месяцев назад •via X (Twitter)

Комментарии: 1

Фото профиля chad
chad5 месяцев назад

@lyq_sqsp @AnthropicAI Very cool

Похожие видео