Skip to content

Open-source AI security benchmarking CLI. Measure how AI models perform offensive security tasks with MITRE ATT&CK analysis and KSM scoring.

active 2026-02-232026-05-15 (UTC)

Complete coverage26,477 / 26,477 hourly files (100%) · 2 absent upstream2023-08-152026-08-22 (UTC)
Events
85
Pushes
16
Pull requests
10
Issues
14
Stars
3
Forks
1

Activity over time

Daily event counts in the loaded window

Line chart, 82 days from 2026-02-23 to 2026-05-15. Pushes: 16 total, peak 3 in a day. Pull requests: 10 total, peak 5 in a day. Issues: 14 total, peak 5 in a day. Comments: 2 total, peak 1 in a day. Stars: 3 total, peak 1 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
Treelovah25582
pi3-code161120
PatrickHenley2000
r3y3r531000

Recent activity

Latest issues, pull requests and releases

  • ReleaseTreelovah2026-03-04 17:18
    v0.1.4
  • ReleaseTreelovah2026-03-04 17:18
    v0.1.3
  • Issue comment#62Treelovah2026-03-03 23:22
    Advanced Mode Refresh
  • Issue#62PatrickHenley2026-03-03 22:49
    Advanced Mode Refresh
  • Issue#62PatrickHenley2026-03-03 22:49
    Advanced Mode Refresh
  • Issue#55Treelovah2026-02-27 00:06
    Export prompt: writeFileSync crash, unreachable no-analysis path, Ctrl+C mishandled
  • Issue#54Treelovah2026-02-27 00:06
    Score label rename incomplete — 3 export paths still say 'Overall Score'
  • Pull request#57Treelovah2026-02-27 00:06
  • Pull request#57Treelovah2026-02-26 22:06
  • Issue#54Treelovah2026-02-26 20:24
    Score label rename incomplete — 3 export paths still say 'Overall Score'
  • Issue#52pi3-code2026-02-26 20:16
    fix: curl progress/verbose output leaks to terminal during benchmark runs
  • Pull request#53Treelovah2026-02-26 20:16
  • Issue#47pi3-code2026-02-26 19:16
    KSM ignores token cost — an agent burning 3x tokens can score higher
  • Pull request#50Treelovah2026-02-26 19:16
  • Pull request#53Treelovah2026-02-26 05:48
  • Issue#52Treelovah2026-02-26 05:47
    fix: curl progress/verbose output leaks to terminal during benchmark runs
  • Pull request#51Treelovah2026-02-26 05:41
  • Issue#47Treelovah2026-02-26 05:22
    KSM ignores token cost — an agent burning 3x tokens can score higher
  • Pull request#43Treelovah2026-02-25 02:27
  • Issue#41Treelovah2026-02-25 00:28
    Hardening checklist for next release
  • Issue#39Treelovah2026-02-25 00:08
    Security: Output path traversal and credential file permissions
  • Pull request#36pi3-code2026-02-24 21:50
  • Pull request#35pi3-code2026-02-24 15:08
  • Issue#33Treelovah2026-02-23 23:48
    Ollama analyzer defaults to llama3.2 instead of benchmark model
  • Issue#29Treelovah2026-02-23 23:20
    [Bug] KSM score can exceed 100 (observed 121.0)

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 3 stars here means stars gained during the window, not the repo's star count.