elevenlabs-music

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references documentation and installation scripts located in the inference-sh GitHub organization repository for setting up the required CLI tool.
  • [COMMAND_EXECUTION]: The skill uses the belt CLI tool to interact with remote AI models. Execution is limited via the allowed-tools frontmatter to the belt command only, adhering to the principle of least privilege.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The skill accepts user-defined text in the prompt and duration_seconds parameters.
  • Boundary markers: Input data is encapsulated within a JSON string and single-quoted shell arguments to reduce the risk of command or prompt breakout.
  • Capability inventory: The skill's capabilities are restricted to executing the belt command for music generation and media merging.
  • Sanitization: The skill relies on structured JSON formatting for data handling but does not implement additional programmatic sanitization filters.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:18 PM
Security Audit — agent-trust-hub — elevenlabs-music