mc-render-compile
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill acts as a transformation layer for external music arrangement specifications (ARR-SPEC) and lyric data (LYR-SPEC) intended for downstream music generation models.
- Ingestion points: The skill processes external data in sections §5.3 (lyric chunking) and §10 (field mapping to ARR-SPEC).
- Boundary markers: While the skill uses structural tags like [Verse] and [Chorus] as delimiters, it does not provide explicit instructions to the agent to treat these data inputs as untrusted or to ignore instructions embedded within the lyrics.
- Capability inventory: The skill is focused on text and logic mapping and does not contain instructions for subprocess calls, file-writing, or network operations.
- Sanitization: No evidence of input validation, escaping, or filtering of the processed specifications or lyrics is provided to prevent potential prompt injection from reaching the generation backends.
Audit Metadata