AIInfoQabout 1 hour ago
Anthropic Launches Opt-In Security Scanner
4 min read
Anthropic launched OSS Scanner on 8th October, a free, opt-in service for open-source projects. The tool uses AI models to identify vulnerabilities and propose patches without human review. Over six months, models found 29,000 candidates, while humans reviewed 6,000. Maintainers receive reports with reproducer and fixes, though some face inflated severity ratings or misunderstandings of threat models.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyAnthropic
