sound-design
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided sound descriptions to generate runnable SuperCollider and Web Audio code, creating a potential attack surface.
- Ingestion points: User-supplied sound descriptions as defined in the
argument-hintfield inSKILL.md. - Boundary markers: There are no explicit delimiters or instructions to ignore malicious commands embedded in the user's description.
- Capability inventory: The skill produces functional code for external environments (SuperCollider and Web Audio API). It does not have access to internal tools for file system or network operations.
- Sanitization: The skill lacks specific sanitization logic for user input, relying instead on its internal synthesis decision matrix to map adjectives to technical parameters.
Audit Metadata