The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to perform file operations using the command mv "{source_file}" "{target_path}". Because the source_file is derived directly from user arguments or external filenames, there is a risk of command injection if the input contains shell metacharacters (e.g., backticks, pipes, or dollar signs) and the underlying execution environment does not handle escaping correctly.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data (file paths and filenames) which are used to construct system paths and execute commands.
Ingestion points: The skill accepts user-supplied <file-path>, <album-name>, and [track-number] as defined in SKILL.md.
Boundary markers: There are no explicit instructions or delimiters defined to ensure the agent treats these inputs as literal data or to ignore instructions that might be embedded in filenames.
Capability inventory: The skill has access to Bash for file system modification, Read for inspecting files, and Glob for file searching.
Sanitization: The instructions do not specify validation or sanitization steps for the inputs before they are used in shell commands or path construction.

import-track