# AI finds 5 out of 7 LibreOffice bugs: Anthropic's Claude

Digest AI · Research · published 2026-11-05T15:53:00Z

Canonical: https://digestai.news/story/ai-finds-5-out-of-7-libreoffice-bugs-anthropic-s-claude

## Summary

On September 21, 2026, non-profit organization The Document Foundation announced that seven vulnerabilities were found in LibreOffice. Five of these were discovered by AI assistant Claude from Anthropic. These include CVE-2026-63278 with a CVSS score of 6.7, which allows sending environment variables or INI file values to an external server via a

## Key points

- AI assistant Claude found five out of seven vulnerabilities in LibreOffice
- Vulnerabilities include CVE-2026-63278 with a CVSS score of 6.7
- Claude's automated analysis uncovered these flaws from June and September

## Why it matters

This highlights Claude’s efficiency in discovering previously overlooked vulnerabilities, potentially impacting software development practices.

## Sources

1. [AI found 5 out of 7 vulnerabilities: LibreOffice highlights Claude's transformation into a 'bug hunter'](https://note.com/note_suke/n/n4a3e02b868f0?hl=en) (note.com, 2026-11-05)

## Cite

Digest AI, "AI finds 5 out of 7 LibreOffice bugs: Anthropic's Claude", 5 November 2026, https://digestai.news/story/ai-finds-5-out-of-7-libreoffice-bugs-anthropic-s-claude

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/ai-finds-5-out-of-7-libreoffice-bugs-anthropic-s-claude.json