fix: close OC-02 gaps in ACP permission + gateway HTTP deny config (#15390) (thanks @aether-ai-agent)

This commit is contained in:
Peter Steinberger
2026-02-13 14:28:50 +01:00
parent 749e28dec7
commit ee31cd47b4
9 changed files with 308 additions and 95 deletions
+1
View File
@@ -6,6 +6,7 @@ Docs: https://docs.openclaw.ai
### Fixes
- Security/Gateway + ACP: block high-risk tools (`sessions_spawn`, `sessions_send`, `gateway`, `whatsapp_login`) from HTTP `/tools/invoke` by default with `gateway.tools.{allow,deny}` overrides, and harden ACP permission selection to fail closed when tool identity/options are ambiguous while supporting `allow_always`/`reject_always`. (#15390) Thanks @aether-ai-agent.
- Security/Audit: distinguish external webhooks (`hooks.enabled`) from internal hooks (`hooks.internal.enabled`) in attack-surface summaries to avoid false exposure signals when only internal hooks are enabled. (#13474) Thanks @mcaxtr.
- Auto-reply/Threading: auto-inject implicit reply threading so `replyToMode` works without requiring model-emitted `[[reply_to_current]]`, while preserving `replyToMode: "off"` behavior for implicit Slack replies and keeping block-streaming chunk coalescing stable under `replyToMode: "first"`. (#14976) Thanks @Diaspar4u.
- Sandbox: pass configured `sandbox.docker.env` variables to sandbox containers at `docker create` time. (#15138) Thanks @stevebot-alive.