Speech Recognition
PassAudited by ClawScan on May 10, 2026.
Overview
This appears to be a straightforward audio transcription skill, but its setup depends on external Python packages and a HuggingFace model that are not captured by an install spec.
This skill looks benign for converting selected voice files to text. Before installing, be aware that you will need to install external Python packages and download a Whisper model yourself; use trusted sources and avoid transcribing private audio unless you are comfortable with how the local environment and dependencies handle it.
Findings (1)
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.
Installing the skill as documented may pull code and model files from external package/model sources, so behavior depends on those upstream artifacts.
The skill relies on external Python packages and a model download. These dependencies are clearly disclosed and align with speech transcription, but they are not pinned or represented in a formal install spec.
pip install pysilk faster-whisper ... python3 -m huggingface_hub snapshot-download --repo-id Systran/faster-whisper-base
Install from trusted package indexes, consider pinning package versions, and verify the HuggingFace model source before use.