elevenlabs-music
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires external components from the inference.sh platform to function. It provides instructions to install the
belt-sh/clipackage and several related skills from theinference-sh/skillsrepository using thenpx skills addcommand. It also points to external documentation hosted athttps://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md. These dependencies are necessary for the skill's primary functionality. - [INDIRECT_PROMPT_INJECTION]: The skill takes user-supplied text for the
promptparameter, which is a vector for indirect prompt injection if the source data is untrusted. - Ingestion points: The
promptparameter in thebelt app run elevenlabs/musiccommand examples. - Boundary markers: None identified; user input is interpolated directly into a JSON string for the CLI command.
- Capability inventory: The skill utilizes the
Bashtool to executebeltCLI commands and can perform file operations (e.g., writing output tomusic.json). - Sanitization: No input sanitization or validation is specified for the prompt input.
Audit Metadata