Skip to content

ASCIT31/Dark-Moon

v1.1.0 Feature

This release adds 2 notable features for engineering teams evaluating rollout.

✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

active-directory ai-agents ai-red-team ai-security-tool autonomous-agents security
+13 more
dynamic-analysis hacking kubernetes llm local-llm mcp multi-agent-systems offensive-security penetration-testing pentesting security-automation security-tools self-hosted

Summary

AI summary

Updates Darkmoon v1.1.0, anti-false-positive, and Result across a mixed release.

Changes in this release

Feature Medium

Persist every finding to server-side store immediately upon discovery.

Persist every finding to server-side store immediately upon discovery.

Source: llm_adapter@2026-06-15

Confidence: high

Feature Medium

Introduce adversarial qualification step assigning status (EXPLOITED/CONFIRMED/UNCONFIRMED) and severity based on demonstrated impact.

Introduce adversarial qualification step assigning status (EXPLOITED/CONFIRMED/UNCONFIRMED) and severity based on demonstrated impact.

Source: llm_adapter@2026-06-15

Confidence: high

Feature Low

Generate final Markdown report from the persisted findings store instead of rewriting from memory.

Generate final Markdown report from the persisted findings store instead of rewriting from memory.

Source: granite4.1:30b@2026-06-15-audit

Confidence: low

Full changelog

Darkmoon v1.1.0

Highlights

Authoritative findings persistence & reporting

  • The pentest engine now persists every finding to a server-side store the moment it is discovered (init → push → finalize), and the final Markdown report is generated from that store instead of being re-written from memory.
  • Result: the report is complete and authoritative by construction — its finding count equals the number of findings actually discovered. No more vulns silently dropped from the report.

Adversarial status qualification (anti-false-positive)

  • A lightweight, adversarial qualification step governs each finding's status (EXPLOITED / CONFIRMED / UNCONFIRMED) and severity by demonstrated impact, not mere observation.
  • Bare HTTP 200s, differential-only responses, payloads echoed in JSON, files served-but-not-executed, and public-by-design secrets are qualified honestly — better qualification, never fewer findings.

Notes

  • Applies across the orchestrator and all specialized sub-agents.
  • conf/tui version: opencode-darkmoon-1.1.0.

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track ASCIT31/Dark-Moon

Get notified when new releases ship.

Sign up free

About ASCIT31/Dark-Moon

All releases →

Related context

Beta — feedback welcome: [email protected]