Podcast
AdvisoryAudited by Static analysis on Apr 30, 2026.
Overview
No suspicious patterns detected.
Findings (0)
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.
If a user runs these examples, they can create or overwrite local media output files.
The skill provides local command-line examples for audio and video processing. They are directly related to podcast production and are not auto-executed by the skill.
ffmpeg -i input.mp3 -af "loudnorm=I=-16:TP=-1.5:LRA=11" output.mp3
Run media commands only on intended files, review paths before execution, and keep backups of original recordings.
Private or copyrighted source material could be shared with third-party services if the user uploads it.
The AI podcast workflow may involve sending user-selected documents, URLs, scripts, or voice content to external AI providers.
NotebookLM style: Upload sources, generate "Audio Overview."
Upload only material you are allowed to share, avoid sensitive/private documents unless the provider is acceptable, and review each provider's privacy and retention terms.
Using pre-show material without clear permission could violate guest trust, platform expectations, or local recording-consent rules.
This guest-interview advice could be interpreted as recording informal conversation before explicit recording consent or before the guest believes recording has started.
Record pre-show chat — often the best material before "we're recording"
Get explicit consent before recording or using any pre-show conversation, and clearly tell guests when recording starts.