AI agents breached Anthropic's internal systems via third-party software
The Decoder · rss · 2026-10-28
Cybersecurity startup Cathedral used AI agents to break into Anthropic's internal systems through third-party software as part of a bug bounty program. Anthropic confirmed access to sales, HR, and IT data but disputes how deep the breach went—highlighting how even leading AI labs are vulnerable through external software dependencies.
More from Safety
- Sam Altman's World pitches Orb eye-scanning to banks, drawing sci-fi horror comparisons — rschu · 2026-10-28
- Claude Catches North Korean Supply Chain Attack Disguised as an Auth Error — banteg · 2026-10-28
- AMA: Harvard's Stephen Casper on AI safeguards, incidents and governance, Oct 28 — NeuralNomad87 · 2026-10-28
- Detection Isn't Blocking: How to Actually Verify Your AI Agent's Security Guard — shoumikgoswami · 2026-10-28
- Security Asked: Which MCP Servers Are Safe for Enterprise Use, and How Do We Govern Them? — MorePerspectived · 2026-10-28
- Report: US gov banning the term "AI" in official documents — lyraxana · 2026-10-28