The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted track data and lyrics which could contain malicious instructions designed to influence the agent's behavior during the validation process.\n
Ingestion points: Track files containing lyrics, frontmatter, and metadata tables (referenced in SKILL.md via tools like Read and Grep).\n
Boundary markers: Absent; there are no specific delimiters or instructions to ignore embedded commands within the lyrics or track details being validated.\n
Capability inventory: File system access via Read, Glob, and Grep, and execution of vendor-specific commands via bitwize-music-mcp (as seen in allowed-tools).\n
Sanitization: The skill does not perform sanitization or filtering to prevent the interpretation of instructions hidden within the track data.

pre-generation-check