Prompt injection defense for agent workspaces. Scan files for injection attempts, analyze content boundaries, detect hidden instructions, and maintain command allowlists. Free alert layer — upgrade to openclaw-bastion-pro for active blocking, sanitization, and runtime enforcement.
- Removed upgrade messaging and references to "bastion-pro" from documentation. - Updated SKILL.md and README to reflect only the open, alert-only features now. - No changes to commands or detection capabilities. - Documentation now focuses solely on features available in the free version.