Soul Petition Gate

Gives your AI agent a formal channel to propose changes to its own soul files (SOUL.md, IDENTITY.md, or any protected workspace file) — without ever letting...

This skill implements what it claims, but do not deploy it as-is on a public or untrusted server. Before installing or running: (1) Ensure the Flask blueprint is only reachable by authorized humans — bind it to localhost or an internal network interface, or put it behind an authenticated admin UI or reverse proxy (OAuth, basic auth over TLS, mTLS, or an API key). (2) Add authentication/authorization checks to the approve/reject/rollback routes (require a reviewer identity, validate tokens, log remote IPs). (3) Consider adding CSRF protections and rate-limiting. (4) Review and test backups and rollback behavior in a safe sandbox to ensure edits are atomic and recoverable. (5) Note the small metadata mismatch: HOOK.md declares node in requirements but the registry metadata lists no required binaries — confirm your environment can run the hook if you enable it. If you cannot secure the endpoints or do not trust the hosting environment, do not run the blueprint; instead run an offline/manual review process where approvals are executed locally by a human operator.

Type: OpenClaw Skill Name: soul-petition-gate Version: 1.0.0 The skill implements a 'Human-in-the-Loop' framework allowing AI agents to propose changes to their own identity files (e.g., SOUL.md) via a structured petition process. The Python backend (soul_petition_routes.py) includes security best practices such as file whitelisting, path traversal prevention using .name, and automatic backups before applying changes. While the Flask blueprint lacks built-in authentication for the approval routes, this is a common characteristic of local development templates and does not indicate malicious intent; the overall design is focused on safety and human oversight.