Agent Lifecycle Manager

Manage full OpenClaw agent lifecycle operations on a node: create/register agents, configure channel bindings, optionally inherit credentials with explicit c...

This skill appears coherent and implements expected lifecycle operations, but it performs destructive and sensitive actions — review before use. Recommendations: - Verify you have a recent backup and test in a non-production environment before deleting agents. - Confirm openclaw CLI is trusted and running with appropriate permissions; the scripts call openclaw to add/remove agents and channels. - Treat Telegram tokens and any auth-profiles.json as sensitive; credential inheritance only occurs if you pass --inherit-auth or set INHERIT_AUTH=1, so avoid enabling that unless explicitly intended. - Run scripts from a controlled working directory (they write archives and state under the current directory by default) to avoid surprising file writes. - Inspect the scripts locally (they are small and readable) before running and ensure audit/log files (AGENT_LIFECYCLE_LOG.md, AGENT_STATUS.md, state/) are written where you expect. If you need higher assurance, provide the openclaw binary provenance and test the scripts with dry-run or a staging instance.

Type: OpenClaw Skill Name: miniade-agent-lifecycle-manager Version: 0.1.2 The skill bundle provides a comprehensive set of administrative tools for managing the lifecycle of OpenClaw agents, including registration, Telegram channel configuration, and safe deletion. While the scripts handle sensitive operations such as copying credential profiles (auth-profiles.json in create-telegram-agent.sh) and managing API tokens, these actions are well-documented, aligned with the stated purpose, and include safety features like mandatory archiving and explicit confirmation strings (delete-agent-safe.sh). No evidence of data exfiltration, obfuscation, or malicious intent was found.