The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input which is then interpolated into shell commands, creating a potential surface for command injection. 1. Ingestion points: The title parameter and the 主题名 (theme name) used in output paths in SKILL.md. 2. Boundary markers: No delimiters or explicit warnings are used to separate user-provided text from the command structure. 3. Capability inventory: The skill executes shell commands using the python interpreter to run a local script (audio_viz.py). 4. Sanitization: There is no mention of sanitization or escaping of special shell characters for the user-supplied strings.
[COMMAND_EXECUTION]: The skill performs its primary function by executing a local Python script through the shell to interface with FFmpeg filters. This is a functional requirement and aligns with the tool's description.

audio-visualizer