The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to perform environment and file system checks, such as verifying directory existence (test -d) and listing files (ls). These commands are used for structural validation and path discovery.
[INDIRECT_PROMPT_INJECTION]: The skill processes content from local album files, which could theoretically contain malicious instructions.
Ingestion points: The agent reads the content of README.md and track markdown files located in {album_path}/tracks/ to extract status and metadata fields.
Boundary markers: There are no explicit delimiters or specific instructions provided to the model to ignore potential commands embedded within the track files or README content.
Capability inventory: The skill possesses the ability to execute Bash commands and use the bitwize-music-mcp toolset based on findings from the ingested files.
Sanitization: No explicit sanitization or validation of the text content within the track files is performed before the model interpolates it for status checking and synchronization logic.

validate-album