Podcast

Create and grow podcasts by planning episodes, producing audio or video, generating clips, and building audience across formats.

This skill is an offline, instruction-only podcast playbook — it appears coherent and safe to read/use. Before relying on it operationally, note: (1) it references third-party services (ElevenLabs, OpenAI TTS, NotebookLM, hosting platforms) that typically require paid accounts and API keys — the skill does not supply or manage those keys, so you must obtain and secure any credentials yourself; (2) it discusses voice cloning and AI-generated content: follow platform terms of service and legal/ethical rules (do not clone voices without consent, disclose synthetic voices where required); (3) example commands (ffmpeg, whisper, pseudocode) assume you will run those tools locally — review and test them in a safe environment before executing; and (4) because the skill can be invoked by the agent autonomously (platform default), avoid giving the agent heightened privileges or secrets alongside this skill unless you trust it to act only within the documented guidance.

Type: OpenClaw Skill Name: podcast Version: 1.0.1 The OpenClaw AgentSkills skill bundle for 'Podcast' is benign. It consists entirely of markdown files providing comprehensive instructions and examples for podcast creation, production, growth, and AI integration. While `ffmpeg` and `whisper` command-line examples are present in `production.md` and `tools.md`, their use is for legitimate media processing tasks (e.g., audio normalization, video trimming, transcription) directly aligned with the skill's stated purpose. There is no evidence of prompt injection against the AI agent, data exfiltration, malicious execution, persistence, or any other intentional harmful behavior. The content is purely informational and task-oriented for podcasting.