security: redact credentials from config.get gateway responses (#9858)

* security: add skill/plugin code safety scanner module

* security: integrate skill scanner into security audit

* security: add pre-install code safety scan for plugins

* style: fix curly brace lint errors in skill-scanner.ts

* docs: add changelog entry for skill code safety scanner

* security: redact credentials from config.get gateway responses

The config.get gateway method returned the full config snapshot
including channel credentials (Discord tokens, Slack botToken/appToken,
Telegram botToken, Feishu appSecret, etc.), model provider API keys,
and gateway auth tokens in plaintext.

Any WebSocket client—including the unauthenticated Control UI when
dangerouslyDisableDeviceAuth is set—could read every secret.

This adds redactConfigSnapshot() which:
- Deep-walks the config object and masks any field whose key matches
  token, password, secret, or apiKey patterns
- Uses the existing redactSensitiveText() to scrub the raw JSON5 source
- Preserves the hash for change detection
- Includes 15 test cases covering all channel types

* security: make gateway config writes return redacted values

* test: disable control UI by default in gateway server tests

* fix: redact credentials in gateway config APIs (#9858) (thanks @abdelsfane)

---------

Co-authored-by: George Pickett <gpickett00@gmail.com>

CHANGELOG.md

@@ -50,6 +50,7 @@ Docs: https://docs.openclaw.ai
 - Web UI: apply button styling to the new-messages indicator.
 - Onboarding: infer auth choice from non-interactive API key flags. (#8484) Thanks @f-trycua.
 - Security: keep untrusted channel metadata out of system prompts (Slack/Discord). Thanks @KonstantinMirin.
+- Security: redact channel credentials (tokens, passwords, API keys, secrets) from gateway config APIs and preserve secrets during Control UI round-trips. (#9858) Thanks @abdelsfane.
 - Discord: treat allowlisted senders as owner for system-prompt identity hints while keeping channel topics untrusted.
 - Slack: strip `<@...>` mention tokens before command matching so `/new` and `/reset` work when prefixed with a mention. (#9971) Thanks @ironbyte-rgb.
 - Security: enforce sandboxed media paths for message tool attachments. (#9182) Thanks @victormier.