mirror of
https://github.com/OpenHands/OpenHands.git
synced 2026-10-07 13:58:33 +08:00
Robert Brennanandopenhands
5a64e0b3c3
* docs: add DefenseClaw security governance integration guide Explains how to integrate DefenseClaw (cisco-ai-defense/defenseclaw) with Agent Canvas and the OpenHands Agent Server without any code-level changes: - Load the DefenseClaw CodeGuard skill for secure-by-default code generation - Route LLM traffic through the DefenseClaw guardrail proxy (localhost:4000) - Pre-install skill scanning via the defenseclaw CLI - Post-generation workspace scanning with CodeGuard - Audit/observability via TUI, OTLP, Splunk, and webhooks Also documents six future code-level extension points (SecurityAnalyzer hook, skill install pipeline gate, hooks integration, UI dashboard, audit bridge, and registry alignment). Co-authored-by: openhands <openhands@all-hands.dev> * docs: replace ASCII diagrams with Mermaid in DefenseClaw integration guide Co-authored-by: openhands <openhands@all-hands.dev> * docs: rename integrating-defenseclaw.md to DefenseClaw.md Co-authored-by: openhands <openhands@all-hands.dev> * docs: simplify Mermaid diagram node labels Co-authored-by: openhands <openhands@all-hands.dev> --------- Co-authored-by: openhands <openhands@all-hands.dev>