Anthropic內部系統被AI代理通過第三方軟體入侵

cathedral, a cybersecurity startup, used ai agents to break into anthropic's internal systems through third-party business software as part of anthropic's own bug bounty program. the ai agents found paths to internal data, including meeting transcripts, salary data, job postings, and slack messages, in under twelve hours. anthropic confirmed that the researchers accessed a limited set of sales, human resources, and it systems, including contact information for some customers and partners, but said chats with claude, source code, and model weights were never exposed. cathedral and anthropic disagree on the duration and scope of the breach, with cathedral saying it took less than twelve hours and anthropic saying the attempts lasted several days. the incident highlights the growing threat of ai agents probing corporate networks around the clock at minimal cost.