mc-sound-design
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a standard for writing timbre descriptors in
roster[].timbreandroster[].notefields (SKILL.md §7). These fields are intended to be consumed by text-based AI music backends. - Ingestion points: Structured data fields in the
rosterobject entry (SKILL.md §7, §3.6). - Boundary markers: No specific delimiters or "ignore" instructions are provided to separate the synthesized description from potential user-injected commands in the generated output.
- Capability inventory: The skill itself contains no executable code, subprocess calls, or network operations, but it describes how to format data for consumption by other agents or models.
- Sanitization: No validation or sanitization rules are defined for the text descriptions or synth parameters.
Audit Metadata