The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied prompts and segment descriptions as inputs for audio generation models, creating a surface for indirect prompt injection.
Ingestion points: prompt and segments parameters in the model_run tool (SKILL.md).
Boundary markers: The instructions do not specify any delimiters or boundary markers for user-provided text.
Capability inventory: The skill utilizes model_run for API interaction and asset_download for retrieving output files.
Sanitization: No input validation or sanitization procedures are mentioned.
[EXTERNAL_DOWNLOADS]: The documentation mentions the installation of supplementary skills from the vendor's official repository (scenario-labs/skills) using CLI tools. These are documented as vendor-owned resources for functional expansion.

scenario-sonilo