- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
Our main goal is to share tips from some well-known bughunters. Using recon methodology, we are able to find subdomains, apis, and tokens that are already exploitable, so we can report them. We wish to influence Onelinetips and explain the commands, for the better understanding of new hunters..
01Result
KingOfBugbounty/KingOfBugBountyTips ↗KingOfBugbounty/KingOfBugBountyTips AI coding statistics: 60%
One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.
02Drivers
What shapes this result
Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.
Assisted or autonomous
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
| Month | Agent share | Considered commits |
|---|---|---|
| 2026-03 | 0% | 2 |
| 2026-07 | 100% | 3 |
Peak month: 100%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 3 | 60% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
cd5a4a0con GitHubdata: add 28 additional DoD assets (2026), organized by branch/agencyClaude Codece71b273on GitHubdocs: translate Feb 2026 CVE section to English, add 5 onelinersClaude Code26121848on GitHubAdd 10 February 2026 CVE Discovery oneliners (recon-focused)Claude Code
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 | 7 |
| Merge commits removed | −2 |
| CI / dependency bots removed | −0 |
| Considered | 5 |
Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.
Continue exploring
Related coding-agent evidence
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 KingOfBugbounty/KingOfBugBountyTips