elevenlabs-music

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the belt CLI and supplementary agent skills from the inference-sh and belt-sh GitHub organizations.
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute belt login for authentication and belt app run for music generation. These are standard operations for interacting with the referenced music generation platform.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides an attack surface where user-supplied text prompts are interpolated into shell commands executed by the agent.
  • Ingestion points: The prompt and duration_seconds parameters defined in SKILL.md examples.
  • Boundary markers: The examples use single-quoted JSON strings to encapsulate input, but no explicit sanitization for shell metacharacters is described.
  • Capability inventory: The skill uses Bash(belt *) which allows shell execution.
  • Sanitization: Absent; the skill relies on the agent to correctly format the CLI call.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 08:14 PM
Security Audit — agent-trust-hub — elevenlabs-music