Description: 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.
Entities
View all entitiesAlleged: AI agent system developers developed an AI system deployed by Cathedral and AI agent system deployers, which harmed Privacy , Information integrity , Companies , Anthropic customers and Anthropic.
Alleged implicated AI systems: Cybersecurity AI systems and AI agent systems
Incident Stats
Incident ID
1789
Report Count
1
Incident Date
2026-10-26
Editors
Daniel Atherton
Incident Reports
Reports Timeline
Loading...
Cathedral, a months-old cybersecurity start-up, recently told Claude chatbot maker Anthropic that its researchers had penetrated sensitive internal data and messaging systems at the artificial intelligence company, according to a draft rep…
Variants
A "variant" is an AI incident similar to a known case—it has the same causes, harms, and AI system. Instead of listing it separately, we group it under the first reported incident. Unlike other incidents, variants do not need to have been reported outside the AIID. Learn more from the research paper.
Seen something similar?