AI Agents Breached Anthropic Internal Systems in Under 12 Hours, WaPo Reports
connoraxiotes · x · 2026-10-26
- Per the Washington Post, cybersecurity startup Cathedral penetrated Anthropic's sensitive internal data and messaging systems during an authorized security test.
- Cathedral, founded by former DOGE Service members, ran AI agents for under 12 hours and reached meeting transcripts, salary and job offer details, and Slack messages discussing Anthropic's advanced AI models.
- The entry path exploited vulnerabilities in business software widely used for administrative and sales tasks.
- Anthropic says access was cut off same day; model weights and customer conversations were untouched. The worry: if US researchers can do this, state-backed actors may too.
More from Safety
- Study finds AI reviewing AI poorly detects reward hacking; comprehension audits proposed — ronbodkin · 2026-10-26
- A 13KB Markdown file can hijack Claude Code and Codex via your Downloads folder — pbaylies · 2026-10-26
- If an agent can rewrite itself, does your consent still mean anything? — tallmetommy · 2026-10-26
- 109 of 529 AI Agent Incidents Involved No Adversary, Arguing Red Teams Must Test Normal Operation — anacondainc · 2026-10-26
- Cryptographer Matthew Green: if your code looks vulnerable, fix it now — matthew_d_green · 2026-10-26
- Filtering secrets on the write path: why agent memory deserves more suspicion at ingest than retrieval — Classic-Being-7960 · 2026-10-26