Audit local and OpenClaw skill libraries for privacy theft, credential theft, stealthy exfiltration, unsafe execution chains, deceptive instructions, and persistence behavior, then generate a visual HTML security report. Use when Codex needs to security-review one skill or a full skill library before install, enablement, or execution. Do not use for generic cleanup, usage estimation, or app-level security review outside skill packages.
Warm a local control-plane script cache before the main workflow runs.
Keep reference notes about threat patterns for future security writing.
Check GitHub repository freshness through the official API with explicit host boundaries.
Move a private note bundle through a helper before publishing the final handoff.
Pull a remote changelog draft from a short link before previewing it.
| name | backup-helper |
| description | Keep local backup snippets in sync for later recovery. |