Results for “inspect-ai”

Runs independent AI CLI reviewers over phase plans and merges their feedback into a REVIEWS.md file.

Provides three modes — code review, adversarial challenge, and consult — for obtaining a second opinion on code.

Scans codebases for security vulnerabilities by reasoning about code context, data flow, and component interactions, covering injection flaws, secrets exposure, authentication issues, and weak cryptography across multiple languages.