Video wird geladen...
Video konnte nicht geladen werden
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... show more
10,125 Aufrufe • vor 5 Monaten •via X (Twitter)
1 Kommentare

chadvor 5 Monaten
@lyq_sqsp @AnthropicAI Very cool



