Dataset: 2026-10-27-catalog-ai-v2
Ruleset: b2e8889c66f7
Scanned: 2026-10-27
Window: February–September 15, 2026

Catalog tracking observation. This repository is measured with the same fixed window and ruleset, but it is not part of the published benchmark or its aggregate claims.

Community curated list of templates for the nuclei engine to find security vulnerabilities.

01Result

projectdiscovery/nuclei-templates ↗

projectdiscovery/nuclei-templates AI coding statistics: 0.4%

of 6,644 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

0.4% agent · top contributor 20%13 contributors

org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

agent commits

6,619

other considered commits

agent contributors

20%

largest contributor

02Drivers

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

25assisted

0autonomous

Assisted — a developer’s identity authored the commit and the agent added itself as co-author. Autonomous — a bot identity authored the commit without a human identity attached.

Agent share by month

Peak month: 1.1%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	17	0.3%
Cursor Agent	Anysphere	4	0.1%
GitHub Copilot	GitHub	4	0.1%

03Evidence

Inspect the matches

Public commit samples let you inspect the signatures behind the aggregate result.

Matched commit samples

350fa830 on GitHubAdd CVE-2026-6377 - Next4Biz CSM - Arbitrary File Read via DownloadFileHanClaude Code
1a6bf695 on GitHubAdd template for CVE-2026-5032 (W3 Total Cache token disclosure)Claude Code
ca56b272 on GitHubAdd template for CVE-2026-20896 (Gitea Docker auth bypass)Claude Code
bf2f50c2 on GitHubfix: set Nuclei-Scanner UA on logs GET; keep wait_for(3) for async jobsCursor Agent
052621aa on GitHubfix: add 3s execution delay to prevent log fetch race conditionCursor Agent
e24e2d65 on GitHubfeat(cve-2025-62593): add unauthenticated RCE template for Ray API (#16961Cursor Agent
225a31a9 on GitHubPotential fix for pull request findingGitHub Copilot
f2474c5b on GitHubfix: correct invalid cve-id field values in classificationGitHub Copilot
04de206f on GitHubAdd FortiSandbox detection templateGitHub Copilot

04Method

What entered the denominator

The result begins with commit history, removes merges and routine automation, and reports literal agent signatures as a lower bound.

Exclusion ledger

Commits in window	8,157
Merge commits removed	−1,442
CI / dependency bots removed	−71
Considered	6,644

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →JavaScript AI coding statisticsCompare evidence across JavaScript repositories →GitHub AI commit analyzerInspect another repository with the same evidence model →

Reproduce this observation

Run the same detector locally.

Deterministic signature matching; no code-style inference. Squash merges can remove trailers, so this result remains a measured floor.

npx qmmit-cli projectdiscovery/nuclei-templates

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	0.2%	1041
2026-03	0.2%	841
2026-04	0.3%	1088
2026-05	0.2%	831
2026-06	0.6%	667
2026-07	0.3%	674
2026-08	0.5%	1129
2026-09	1.1%	373