Anthropic uses Claude to shrink open-source attack surface
What happened
A Hacker News front-page report on October 21 covers Anthropic research that used Claude to reduce code attack surface. The study analyzed 25 open-source projects spanning more than 5 million lines of code and found 493 issues, focusing on unnecessary exposure under default configurations, configuration combinations that weaken security controls, and code reachable before authentication or protocol state checks. Anthropic packaged the method as a reusable skill. In the OpenSSH case, the fix shipped in version 10.6 and removed about one fifth of the code previously reachable by unauthenticated clients in the default build. The skill is slated for integration into OSS-Scanner.
Written by AI from the coverage · updated 2 hours ago
Coverage
Follow the reports to see the story from different sides.
- Hacker News front pagePickAnthropic used Claude to shrink code attack surface across 25 open-source projects
Anthropic ran Claude over 25 open-source projects, more than 5 million lines of code, and found 493 issues. The review looked at unnecessary exposure under default configs, config combinations that weaken security controls, and code reachable before auth or protocol state checks. The method is packaged as a reusable skill. In OpenSSH, fixes shipping with 10.6 removed about a fifth of the code unauthenticated clients could previously reach in the default build.
Heat over time
Not enough continuous observations to draw a trend yet.