suno-by-acedatacloud
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill has a standard exposure surface for indirect prompt injection via external API responses.
- Ingestion points: Untrusted data may enter the context via
suno_list_modelsandsuno_get_taskoutputs as defined inSKILL.md. - Boundary markers: The instructions do not specify explicit delimiters for API response data.
- Capability inventory: The skill is limited to calling specific Suno-related MCP tools; it lacks shell access, file system write permissions, or general network access.
- Sanitization: No specific sanitization logic is implemented for the API responses.
- [SAFE]: The skill includes explicit instructions for the AI agent to avoid requesting, printing, or otherwise exposing the API token in conversation or command arguments, following credential safety best practices.
Audit Metadata