TL;DR: Instead of hunting vulnerabilities one by one, shrink the code that can be reached. Claude analyzed 25 open-source projects, reported 493 issues, and cut about 16% of OpenSSH's pre-authentication code.
Title: Using Claude to reduce the attack surface of code
URL:
Key points
ใป๐บ๏ธ 25 projects and 5M+ lines, with 17,000+ config options inventoried (3,842 security-relevant)
ใป๐ 93 unnecessary pre-auth surfaces in default configs, plus 61 combos that silently weaken a pre-auth control
ใปโ๏ธ 162 option combinations accepted with no warning, 94 of them silently disabling a security control
ใป๐ Hostname-based rules relying on reverse DNS fail open when it's off (4 projects)
ใปโณ A config conflict dropped a certificate requirement for 21 years, undocumented
ใป๐ OpenSSH: about 4,500 lines of experimental ML-DSA-44 code reachable by unauthenticated clients removed, shipped in 10.6
Making unknown bugs unreachable seems more practical than fixing them one at a time.
#
AISecurity# #
OpenSSH#