daily-news-caster
PassAudited by ClawScan on May 1, 2026.
Overview
This instruction-only skill is coherent with its stated purpose, but users should notice that it orchestrates other local skills, runs command-line tools, uses network/TTS services, and may use an optional TTS API key or reference audio.
This skill appears reasonable for making a news podcast, but install it only if you are comfortable with it running the local news and TTS skills, creating podcast files in your workspace, and using any configured TTS service or API key. Review the dependency skills before use, especially if you plan to provide reference voice audio.
Findings (4)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
The agent may create or overwrite local podcast-related files and run local tools to fetch news and generate audio.
The skill instructs the agent to run local Python scripts and ffmpeg commands. This is central to generating the podcast and is disclosed, but users should recognize it involves command execution and local file creation.
Run the script to fetch real-time news... python3 skills/news-aggregator-skill/scripts/fetch_news.py --source all --limit 10 --deep ... ffmpeg -f concat -safe 0 -i list.txt -c copy podcast_output.wav
Run it in an appropriate workspace, review the generated filenames, and ensure the dependency skills and ffmpeg behavior are acceptable before use.
The safety and behavior of the final workflow also depend on the local news-aggregator-skill, tts skill, python3, and ffmpeg installation.
The skill relies on locally installed dependency skills and binaries that are not included in this artifact. The workflow discloses this and tells the user not to auto-install missing skills, so this is a supply-chain notice rather than a concern.
dependencies:\n skills:\n - news-aggregator-skill\n - tts\n binaries:\n - python3\n - ffmpeg
Review the installed dependency skills and their SKILL.md/code before using this orchestration skill.
If voice-cloning is used, the TTS dependency may access a NOIZ account or API quota using the user's key.
The skill itself does not require credentials, but one dependency may use an API key for optional voice-cloning features. This is purpose-aligned and disclosed, but credential use should be reviewed.
The `tts` dependency may require `NOIZ_API_KEY` for voice-cloning features (noiz backend); without it, guest-mode voices work out of the box.
Use the minimum necessary TTS credential, verify the tts skill's documented credential handling, and avoid enabling voice cloning unless needed.
Podcast text and any provided voice reference audio may be processed by the TTS dependency or its backend.
The workflow indicates that generated script text, and possibly user-provided reference audio, may be passed through a TTS API/backend. This fits the stated purpose but is sensitive enough for users to notice.
To avoid sending the entire script to the API at once, you must generate the audio sentence by sentence... If the user provided reference audio files for the two roles, use them via the `--ref-audio` flag
Do not include private or sensitive content in the podcast script or reference audio unless you trust the TTS backend and have reviewed its data handling.