[PR #269] [MERGED] [codex] docs: clarify current PentAGI capability boundaries #285

Closed
opened 2026-06-06 22:10:03 -04:00 by yindo · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/vxcontrol/pentagi/pull/269
Author: @mason5052
Created: 4/16/2026
Status: Merged
Merged: 4/23/2026
Merged by: @asdek

Base: feature/next-releaseHead: codex/issue-35-capability-boundaries-docs


📝 Commits (1)

  • ea8aa20 docs: clarify current PentAGI capability boundaries

📊 Changes

1 file changed (+7 additions, -0 deletions)

View changed files

📝 README.md (+7 -0)

📄 Description

Summary

  • adds a short Current Capability Boundaries section to README.md
  • clarifies what PentAGI supports today versus what is still conceptual
  • points readers to the existing reporting and provider docs instead of implying unsupported BAS-style workflows or JSON flow-report export

Problem

Issue #35 asks whether PentAGI already supports internal pentest / BAS-like workflows, specific report outputs, and flexible provider setup. The repo already contains pieces of that answer, but the README did not state the current capability boundaries in one place, which makes it easy to over-assume what is available today.

Related to #35.

Solution

  • add a focused README clarification right after the Features section
  • state that PentAGI is an autonomous and assistant-guided pentesting platform, not a CALDERA-style BAS or predefined adversary emulation product
  • describe BAS-like agent-authored attack scripts as conceptual or future work, not an implemented feature
  • document the current flow report UI reality: web view, copy to clipboard, Markdown download, and PDF download
  • point readers to the existing custom/OpenAI-compatible provider configuration docs and the vLLM guide

User Impact

  • sets clearer expectations for users evaluating PentAGI for internal pentest or BAS-style use cases
  • reduces confusion around what reporting/export options are available right now
  • makes provider flexibility easier to discover from the main README

Test Plan

  • verified maintainer guidance in issue #35 before drafting the wording
  • verified OpenAI-compatible endpoint support in README.md and backend/docs/llms_how_to.md
  • verified current flow report UI actions in frontend/src/pages/flows/flow.tsx
  • verified no documented JSON flow-report export for flow reports
  • ran git diff --check

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/vxcontrol/pentagi/pull/269 **Author:** [@mason5052](https://github.com/mason5052) **Created:** 4/16/2026 **Status:** ✅ Merged **Merged:** 4/23/2026 **Merged by:** [@asdek](https://github.com/asdek) **Base:** `feature/next-release` ← **Head:** `codex/issue-35-capability-boundaries-docs` --- ### 📝 Commits (1) - [`ea8aa20`](https://github.com/vxcontrol/pentagi/commit/ea8aa205bcd5fb9ce0b84aef1cd3d7490329b1ff) docs: clarify current PentAGI capability boundaries ### 📊 Changes **1 file changed** (+7 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `README.md` (+7 -0) </details> ### 📄 Description ### Summary - adds a short `Current Capability Boundaries` section to `README.md` - clarifies what PentAGI supports today versus what is still conceptual - points readers to the existing reporting and provider docs instead of implying unsupported BAS-style workflows or JSON flow-report export ### Problem Issue #35 asks whether PentAGI already supports internal pentest / BAS-like workflows, specific report outputs, and flexible provider setup. The repo already contains pieces of that answer, but the README did not state the current capability boundaries in one place, which makes it easy to over-assume what is available today. Related to #35. ### Solution - add a focused README clarification right after the Features section - state that PentAGI is an autonomous and assistant-guided pentesting platform, not a CALDERA-style BAS or predefined adversary emulation product - describe BAS-like agent-authored attack scripts as conceptual or future work, not an implemented feature - document the current flow report UI reality: web view, copy to clipboard, Markdown download, and PDF download - point readers to the existing custom/OpenAI-compatible provider configuration docs and the vLLM guide ### User Impact - sets clearer expectations for users evaluating PentAGI for internal pentest or BAS-style use cases - reduces confusion around what reporting/export options are available right now - makes provider flexibility easier to discover from the main README ### Test Plan - verified maintainer guidance in issue #35 before drafting the wording - verified OpenAI-compatible endpoint support in `README.md` and `backend/docs/llms_how_to.md` - verified current flow report UI actions in `frontend/src/pages/flows/flow.tsx` - verified no documented JSON flow-report export for flow reports - ran `git diff --check` --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
yindo added the pull-request label 2026-06-06 22:10:03 -04:00
yindo closed this issue 2026-06-06 22:10:03 -04:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: vxcontrol/pentagi#285