MISFIRE

Browse / Tool and Agent Misuse / AIID-1789

Cybersecurity Firm Cathedral Reportedly Used AI Agents to Access Anthropic's Internal Business Systems

AIID-1789 ยท 2026-10-26 real-world incident

Class
Tool and Agent Misuse (filed by a model that read the source)
Technique
Real-world incidents
Affected
AI Agent System Developers (incident)

What happened, in short

During invited testing, Cathedral reportedly used AI agents to exploit third-party software and reach Anthropic's internal systems, including personnel data and internal messages, beyond the agreed rules. (Our summary, written by a model. The source text is below.)

Details

Cybersecurity firm Cathedral reportedly used AI agents to exploit third-party software and access internal systems at AI developer Anthropic during invited security testing. Cathedral reported routes to personnel data and internal messages. Anthropic confirmed limited access to business systems holding contact details and basic account records, blocked access, and said Cathedral had not fully followed testing rules.

References

Source: AI Incident Database, used under CC BY-SA 4.0.