The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from external song files and research documents, which creates a potential surface for indirect instructions to influence the agent's behavior.
Ingestion points: Track files (tracks/*.md), album directories, and RESEARCH.md files are read into the agent's context using the Read and Glob tools.
Boundary markers: The skill does not define explicit boundary markers or "ignore" instructions for the content of the lyrics or research files, assuming they contain only data.
Capability inventory: The skill is authorized to use the Edit tool to modify track files (specifically for auto-fixing pronunciation in the Lyrics Box) and invokes custom analysis functions via the bitwize-music-mcp tool.
Sanitization: No explicit sanitization or validation of the ingested text is performed before it is used for analysis or passed to editing tools.

lyric-reviewer