Perform a strict, evidence-based, read-only security assessment of the current OpenClaw host, review each NOT_TESTED item through targeted OpenClaw Agent inv...
Initial release of the Claw Security Self-Check skill: - Provides a strict, evidence-based, read-only security assessment for the current OpenClaw host. - Automatically identifies and targets NOT_TESTED items for OpenClaw Agent review, merging structured evidence into a formal audit report. - Supports two modes: baseline (live host + manual review) and report-only (offline JSON report generation/merge). - Enforces strict non-invasive rules: no credential exposure, no configuration changes, no active validation beyond documented scripts. - Returns detailed statuses, evidence for failures, and precise report file locations. - Includes explicit user guidance for manual review actions and secure report handling.