Claude audit of 25 open-source projects finds nearly 500 security issues
Anthropic used Claude to analyze 25 major open-source projects written in C, C++, Java, PHP and Python, scanning more than five million lines of code and reporting almost 500 security issues, according to TechRadar. The vendor account says findings included security controls disabled by conflicting settings, sensitive code reachable before authentication, and one flaw that went undetected for 21 years. Anthropic presented OpenSSH as its case study, saying it disclosed exposed pre-authentication code paths and that OpenSSH fixed them in version 10.6, making roughly 20% of the code unreachable to unauthenticated clients.
Anthropic says it packaged the techniques into a reusable Claude skill to be integrated into OSS-Scanner, its free opt-in security scanning service for open-source projects, which would examine default configurations, pre-authentication code paths and conflicting settings.
- Anthropic used Claude to analyze 25 open source projects and uncovered nearly 500 security issues
- Research found exposed pre-authentication code paths, conflicting security settings, and long-hidden flaws
- AI identified attack-surface reductions that removed unnecessary code exposure before vulnerabilities could be exploited
Anthropic recently used Claude to analyze 25 major open source projects written in C, C++, Java, PHP, and Python, in search of security issues. It found almost 500 of them, including security controls turned off by conflicts in settings, sensitive code accessible before authentication, and even a vulnerability that sat in the code for 21 years.
This wasn’t a standard hunt for vulnerabilities. In its report, Anthropic argues that looking for individual vulnerabilities is a Sisyphean task that scales poorly and never guarantees security. Instead, it thinks defenders should turn towards reducing software attack surfaces by restricting unnecessary access to potentially exploitable code.
“A defender who reduces unnecessary attack surface in their code reduces the risk from all of the unknown vulnerabilities in that code at once—including any that are already being quietly exploited,” Anthropic said.