scenario-ace-step
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a clear, functional set of instructions for interacting with music production models on the Scenario platform.
- [INDIRECT_PROMPT_INJECTION]: The skill consumes user-provided lyrics and style prompts. This represents a standard attack surface for indirect prompt injection, but it is inherent to the music generation use case. The instructions guide the agent to use structured section tags (e.g., [Verse], [Chorus]), which helps establish content boundaries.
- [EXTERNAL_DOWNLOADS]: The documentation suggests that the user can install related skills using the command
npx skills add scenario-labs/skills. This is a legitimate instruction for managing official vendor tools and does not constitute an unauthorized or hidden download. - [COMMAND_EXECUTION]: The skill mentions various MCP tools (e.g.,
model_run,asset_download,search) and a first-party utilitymodel_scenario-audio-cut. These are standard tools within the vendor's ecosystem for handling audio assets and model inference.
Audit Metadata