The Agent Skills Directory

[SAFE]: The skill performs legitimate analysis of lyrics to resolve phonetic ambiguities and improve audio generation quality.
[SAFE]: File system operations (Read, Edit, Write) are scoped to managing lyrics and pronunciation overrides, which is consistent with the skill's stated purpose.
[PROMPT_INJECTION]: The skill processes untrusted user data (lyrics) and has the capability to write to the file system, representing an indirect prompt injection surface. Evidence: (1) Ingestion points: Lyrics or track file paths in $ARGUMENTS. (2) Boundary markers: Absent. (3) Capability inventory: Read, Write, Edit, Grep, Glob, and bitwize-music-mcp. (4) Sanitization: No explicit validation or escaping of external content before processing.

pronunciation-specialist