elevenlabs-music-generation
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill takes user-supplied prompts and lyrics to generate music, creating a standard input surface for AI interaction.
- Ingestion points: The
promptfield in the command-line examples provided inSKILL.md. - Boundary markers: User input is encapsulated within a JSON object passed to the CLI
--inputparameter, providing clear separation. - Capability inventory: The skill restricts tool execution to the
runcomfycommand via theallowed-toolsfrontmatter field. - Sanitization: The documentation explicitly states that the CLI transmits data as JSON to avoid shell injection vulnerabilities.
- [EXTERNAL_DOWNLOADS]: The skill requires the
@runcomfy/clipackage from the NPM registry. This is a legitimate dependency provided by the service vendor for the skill's stated purpose. - [CREDENTIALS_UNSAFE]: The documentation informs users about the local storage location of the API token (
~/.config/runcomfy/token.json). Providing this information is considered a transparent best practice for CLI tool integration and does not constitute a security vulnerability.
Audit Metadata