Autonomous AI Security Auditing of Webmin 2.670: 507 Newly Discovered Vulnerabilities

An experienced security researcher translated techniques developed before modern AI into a fully autonomous Codex campaign against Webmin. The campaign delivered 507 canonical, reproduced findings at a pinned Webmin 2.670 revision with 44,297 tracked files, 476,216 Perl/CGI lines overall, and 386,178 production code lines measured by cloc. Its 524 applicability paths have CVSS 4.0 Base assessments and explicit conditions. Execution consumed 8,347,303,160 model tokens; the same token mix at the current Standard API rates would cost about US$4,578. Among paths without recorded special conditions, 48 of 73 XSS and 38 of 51 privilege-escalation paths match module gates present in at least 80% of 6,756 sampled host profiles. The catalogue also records 567 confirmed historical issues and 95 hardening observations. In the author's judgment, the audit captured over 90% of classic defects at the pinned revision, possibly every XSS. The author has observed a sharp rise in AI-produced findings within the past two months, especially in recent weeks. This case study records what a fully autonomous, researcher-designed campaign can achieve at this rapidly changing point. The deposit includes the paper, a structured public data archive, and a checksum manifest. Companion fingerprinting software is available at DOI 10.5281/zenodo.24367586.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-19
DOI
https://doi.org/10.5281/zenodo.24367597
Primary Topic
Web Application Security Vulnerabilities
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Autonomous AI Security Auditing of Webmin 2.670: 507 Newly Discovered Vulnerabilities

Armin Šupuk
Zenodo (CERN European Organization for Nuclear Research)
Web Application Security Vulnerabilities
preprint

Autonomous AI Security Auditing of Webmin 2.670: 507 Newly Discovered Vulnerabilities

Armin Šupuk
preprint en

Abstract

An experienced security researcher translated techniques developed before modern AI into a fully autonomous Codex campaign against Webmin. The campaign delivered 507 canonical, reproduced findings at a pinned Webmin 2.670 revision with 44,297 tracked files, 476,216 Perl/CGI lines overall, and 386,178 production code lines measured by cloc. Its 524 applicability paths have CVSS 4.0 Base assessments and explicit conditions. Execution consumed 8,347,303,160 model tokens; the same token mix at the current Standard API rates would cost about US$4,578. Among paths without recorded special conditions, 48 of 73 XSS and 38 of 51 privilege-escalation paths match module gates present in at least 80% of 6,756 sampled host profiles. The catalogue also records 567 confirmed historical issues and 95 hardening observations. In the author's judgment, the audit captured over 90% of classic defects at the pinned revision, possibly every XSS. The author has observed a sharp rise in AI-produced findings within the past two months, especially in recent weeks. This case study records what a fully autonomous, researcher-designed campaign can achieve at this rapidly changing point. The deposit includes the paper, a structured public data archive, and a checksum manifest. Companion fingerprinting software is available at DOI 10.5281/zenodo.24367586.

Zenodo (CERN European Organization for Nuclear Research)
Web Application Security Vulnerabilities
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon