Fieldy AI Webhook

This skill appears to do what it says: parse incoming webhook payloads, log transcripts to <workspace>/fieldy/transcripts, and trigger the agent when a wake word is detected. Before installing: 1) Do not drop the script into a privileged system directory — use a workspace owned by a non-root user. The SKILL.md suggests /root/...; adapt that to a non-root path if appropriate. 2) Protect your Moltbot hooks token: prefer sending it in an Authorization header rather than embedding it in a public URL query string, and rotate it if exposed. 3) Transcripts may contain sensitive data — ensure the transcripts directory has appropriate filesystem permissions and retention policies. 4) If you need stricter verification of webhook origin (signatures, IP allowlist), add that into the transform — the current script does not validate source authenticity. 5) Review and test the transform in a safe environment to confirm the workspace detection logic uses the intended directory and that no unexpected files are read/written.