elevenlabs-music
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
belt-sh/clivia npx and add additional skills from theinference-shorganization. These resources originate from the vendor's own infrastructure and established service provider repositories. - [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted text strings to generate music.
- Ingestion points: The
promptparameter defined inSKILL.mdis interpolated into shell commands. - Boundary markers: Absent; the instructions do not include delimiters or warnings to ignore instructions embedded within the music prompts.
- Capability inventory: The skill uses the
Bashtool to executebeltcommands, which involves network interaction and local shell execution. - Sanitization: No sanitization or validation of the input prompt is performed within the skill's instructions.
- [COMMAND_EXECUTION]: The skill uses the
Bashtool to run thebeltCLI. The scope is limited to thebeltcommand as defined in theallowed-toolsfrontmatter, which follows the principle of least privilege.
Audit Metadata