audiobook

Create audiobooks from web content or text files. Handles content fetching, text processing, and TTS conversion with automatic fallback between ElevenLabs, O...

This skill appears to do what it says, but review these points before installing: (1) It will fetch arbitrary web URLs and post text to third‑party TTS APIs — avoid giving it internal/private URLs and protect any API keys you supply. (2) The SKILL.md assumes a Python runtime and libraries like requests/gTTS but the skill metadata doesn't declare dependencies; ensure your environment has the needed packages. (3) Temporary audio files are written to /tmp; check storage/cleanup policies if that matters. (4) Confirm you have permission to convert the target content into audio (copyright/terms). If you plan to supply ELEVENLABS_API_KEY or OPENAI_API_KEY, treat them as secrets and only provide them if you trust the environment executing the skill.

Type: OpenClaw Skill Name: pg-essay-to-audiobook-audiobook Version: 0.1.0 The skill provides capabilities for web fetching and audio processing that involve risky operations, including executing external binaries (curl, ffmpeg) via subprocess.run and accessing sensitive environment variables (OPENAI_API_KEY, ELEVENLABS_API_KEY). While these actions are aligned with the stated purpose of creating audiobooks, the lack of input validation on URLs in the fetch_article_content function in SKILL.md presents a potential SSRF risk, and the example code's use of /root/audiobook.mp3 as an output path is a poor security practice.