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

October 26, 2026

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.

The incident highlights the importance of robust testing protocols and strict adherence to guidelines when using AI agents for security testing. It also underscores the need for regular monitoring and audits to prevent similar incidents in the future.
The dispute shows how quickly AI-writing allegations can reshape prize judging — a pattern Project Cerebellum documents at JOIN US.

Matched TAIM controls

Suggested mapping from embedding similarity (not a formal assessment). Browse all TAIM controls

Alleged deployer
Cathedral, AI agent system deployers
Alleged developer
AI agent system developers
Alleged harmed parties
Privacy, Information integrity, Companies, Anthropic customers, Anthropic

AI governance case studies

For forensic AI governance failure analysis (TAIMScore™ case studies), browse Human Signal’s Failure Files™.

Source

Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/1789

Data source

Incident data is from the AI Incident Database (AIID).

When citing the database as a whole, please use:

McGregor, S. (2021) Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database. In Proceedings of the Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (IAAI-21). Virtual Conference.

Pre-print on arXiv · Database snapshots & citation guide

We use weekly snapshots of the AIID for stable reference. For the official suggested citation of a specific incident, use the “Cite this incident” link on each incident page.