OpenClaw v2026.5.7: security hardening and context reliability
The brief
OpenClaw v2026.5.4-5.7 add authorization-gated skill dispatch, admin-scoped memory writes, skill snapshot invalidation on session reset, stale-context purging, and compaction summary token clamping after a rough.
Sources
- aifirst-reviewgithub.com
- Source codegithub.com