← All news

FreeStack News ·

Anthropic OSS Scanner offers free scans, with reports that have no human review

Accepted open-source projects can get periodic scans at no cost. AI reports arrive without human review and may be wrong. Core maintainers apply through GitHub.

FreeStack News illustration of a shield scanning code for OSS Scanner, with free security scans, reports can be wrong and announcement, not tested labels

What changed

Anthropic announced OSS Scanner on October 8. Accepted open-source projects can receive periodic security scans by Anthropic's strongest models at no cost. This is an opt-in service. Core maintainers enroll through a pull request to the official GitHub repository. Acceptance is case by case.

Why it matters

Reports explain a possible vulnerability and include a self-contained reproducer. A candidate patch is included when available. The service aims to give maintainers findings sooner, without waiting for Anthropic's normal human-review process. Maintainers still need to check and triage each report.

Reality Check

Reports are fully model-generated and have no human review or triage before delivery. They may be incorrect or invalid. Eligibility focuses on established projects with a critical impact on infrastructure and user security, not every personal project. We have not tested the scanner. This is announcement coverage, with no affiliate link.

Official source: View the maker's update ↗. Our short is an explanation, not a hands-on product test unless we explicitly say otherwise.

More FreeStack News →