AI Wiki · Mediocre Security
IncidentIncidents

Cathedral agents breach Anthropic (authorized test)

Security startup Cathedral's AI agents got into business systems around Anthropic in under 12 hours through two third-party software flaws.

What happened

security startup Cathedral’s AI agents got into sensitive business systems around Anthropic in under 12 hours, through two third-party software flaws (Anthropic says it saw several days of attempts, shut the access points and notified federal authorities).

Timeline

Every dated event in the wiki that involves Cathedral agents breach Anthropic (authorized test), newest first.

Connections

Cathedral agents breach Anthropic (authorized test) and everything one link away. Drag to move, scroll to zoom, click a node to open it.Open in the full graph →

What links here

AI lab Anthropic

Sources

  1. Decrypt, “AI Agents Found a Way Into Anthropic's Business Systems in Under 12 Hours”, Oct 26 2026 (citing the Washington Post)