The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a local script tools/music_gen.py to generate music, extract stems, and manage presets. This command execution is the primary and intended function of the skill.
[INDIRECT_PROMPT_INJECTION]: The skill identified an attack surface where user-provided prompts and lyrics are passed to the music generation engine. Given the context of music generation, this risk is assessed as safe.
Ingestion points: Untrusted user input enters the system via the --prompt and --lyrics arguments in the SKILL.md usage examples.
Boundary markers: No specific boundary markers or instructions to ignore embedded commands are provided for the music generation tool's input.
Capability inventory: The skill's primary capability is executing the tools/music_gen.py script and writing temporary lyric files.
Sanitization: No explicit sanitization or filtering of user input is described in the skill instructions.

acestep