Claude扫描25个开源项目,标出493个暴露问题
Anthropic 安全工程师 Chris Rohlf 发布了 Frontier Red Team 关于自动化攻击面分析与缩减的研究:用 Claude 梳理某次部署实际需要暴露的代码,再把其余部分移除或加上访问限制。Anthropic 称 Claude 扫描了 25 个开源项目、超过五百万行 C、C++、Java、PHP 和 Python 代码,标出 493 个问题;The Next Web 报道称它梳理了逾 1.7 万个配置选项并发现 162 组被接受的敏感安全组合,在 OpenSSH 中发现约 4,500 行默认状态下未认证客户端即可触达的后量子签名代码,相关修复已在 10.5 和 10.6 版本发布。Anthropic 表示已将这三类技术合并为一个可复用的 Claude skill,并正努力将其整合进 OSS-Scanner;同时也承认这些方法并不能消除未知漏洞,只是让它们更难被触达。
Anthropic 表示,即便在全球被审计得最充分的 OpenSSH 代码中,多余的可达性依然存在,并称这项工作说明前沿模型不仅能发现和利用漏洞,也能用于网络防御。
Chris Rohlf
Over the past year, we’ve published lots of data that shows that frontier AI models are more than capable of discovering and exploiting security vulnerabilities. Showing how previously unknown vulnerabilities might be exploited is, however, only the start of what frontier AI models can do for cyber defense. In this post, we summarize some of our initial research into automated attack surface analysis and reduction: the process of using AI models to map the code that is reachable, then removing or restricting access to anything than a given deployment doesn’t need to expose.
Automated attack surface analysis and reduction can meaningfully improve the security of deployed software in the near term. Securing software by finding and fixing individual vulnerabilities alone scales poorly: fixing even a critical vulnerability tells you nothing about the vulnerabilities that remain. By contrast, reducing code reachability can reduce the severity of unknown vulnerabilities, including the ones that might be under active exploitation. These techniques don’t remove the unknown vulnerabilities in the code, but they do make the vulnerabilities harder to reach, and thereby reduce their severity. Minimizing codebases’ attack surface results in better security without ever having to find or fix an individual vulnerability.