Moses Postures

MO§ES™ Posture Controls — Enforces transaction and execution policies across all agents. SCOUT=read-only, DEFENSE=protect+confirm, OFFENSE=execute within mod...

This skill appears internally consistent for enforcing posture rules, but before installing: 1) Install and inspect the moses-governance bundle (especially the init_state.py script) to verify it does only what you expect. 2) Confirm the location and permissions of ~/.openclaw/governance/state.json and ensure only trusted operators can edit it. 3) Ask where 'logs' (execution decisions and rationales) will be written and who can access/transmit them; if unspecified, require the skill to log to a controlled, local path. 4) If you are concerned about broad 'verification' behaviors, limit agent autonomy or require operator confirmations for sensitive actions. If any of these items are unacceptable or the dependent bundle cannot be reviewed, consider not installing or running the skill with restricted agent privileges.

Type: OpenClaw Skill Name: moses-postures Version: 1.0.2 The skill bundle defines a governance framework for an AI agent, establishing operational 'postures' (SCOUT, DEFENSE, OFFENSE) to restrict or permit transactions. The SKILL.md file provides safety-oriented instructions to the agent, such as enforcing read-only modes and requiring operator confirmation for transfers. No malicious code, exfiltration logic, or harmful prompt injections are present; the skill appears designed to enhance agent safety and control through local state management in ~/.openclaw/governance/state.json.