Loading video...

Video Failed to Load

Go Home

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 views • 5 months ago •via X (Twitter)

1 Comments

chad's profile picture
chad5 months ago

@lyq_sqsp @AnthropicAI Very cool

Related Videos