audio-quality-check
Security checks across malware telemetry and agentic risk
Overview
The visible artifacts behave like a local audio-analysis helper, with only expected risks from running media tools and Python dependencies on recordings you choose.
This skill appears reasonable for local audio-quality checks. Before installing, be comfortable running ffmpeg and Python audio libraries locally, use trusted dependency sources, and only point the script at recordings you intend to analyze because call recordings may contain sensitive personal or business information.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
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.
Running the skill can execute local media-processing tools and read/process the recordings you point it at.
The bundled script invokes local media binaries such as ffprobe/ffmpeg on user-supplied audio paths. This is expected for the skill's purpose and uses argument lists rather than shell strings, but users should know external programs will run locally.
subprocess.run(["ffprobe", "-v", "quiet", "-print_format", "json", "-show_streams", str(audio_path)], capture_output=True, text=True)
Install ffmpeg/ffprobe from trusted sources and run the script only on recording directories you intend to analyze.
Installing dependencies may pull the latest package versions from package indexes, which can change over time.
The skill asks users to install several third-party Python packages without version pins or a lockfile. This is purpose-aligned but leaves dependency versions and provenance to the user's environment.
Install all Python deps: `pip3 install numpy soundfile scipy pyloudnorm pesq pystoi librosa`
Use a virtual environment, install from trusted package sources, and consider pinning dependency versions if reproducibility or supply-chain control matters.