正在加载视频...

视频加载失败

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 次观看 • 5 个月前 •via X (Twitter)

1 条评论

chad 的头像
chad5 个月前

@lyq_sqsp @AnthropicAI Very cool

相关视频