# Anthropic says Claude found 493 issues in 25 open-source projects

- Published: 2026-10-20T00:00:00.000Z
- Updated: 2026-10-25T10:06:21.691Z
- Section: Models
- Topics: Code, Security, Research
- Page: https://aidailyjournal.com/en/n/2026/10/19/anthropic-says-claude-found-493-issues-in-25-open-source-projects/
- Sources: [Anthropic](https://anthropic.com/research/attack-surface-reduction)

## Summary

In a post by Chris Rohlf, Anthropic presents initial results from using Claude to analyze and automatically reduce the attack surface of large open-source codebases. The company says the model examined 25 projects, totaling more than five million lines of code, and found 493 issues.

The approach aims to identify unnecessarily reachable code and place it behind appropriate controls, such as authentication, user interaction, or later protocol stages. Anthropic highlights three methods: reviewing default configuration, detecting problematic combinations of options, and finding security-sensitive code that runs too early. The company says reducing code reachability does not eliminate unknown vulnerabilities, but can make them harder to exploit and reduce their severity.

## Why it matters (editorial interpretation)

The approach described could give maintainers a way to prioritize reviews in large codebases by limiting unnecessarily reachable paths. Anthropic itself notes that this does not eliminate unknown vulnerabilities, but may make them harder to exploit and reduce their severity.

_Summary written by AI Daily Journal in its own words, based on the sources above. For details, read the original articles._