elevenlabs-sound-effects

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Recommends installing the 'belt' CLI skill from 'belt-sh/cli' and fetches installation guidelines from the 'inference-sh' GitHub organization.
  • [COMMAND_EXECUTION]: Provides templates and examples for using the 'belt' command-line interface to interact with remote AI services, including authentication and application execution.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: User-provided text descriptions are processed in SKILL.md through CLI parameters.
  • Boundary markers: Input is structured within JSON objects passed to the command line, helping to distinguish data from instructions.
  • Capability inventory: The skill facilitates network-based sound generation through the 'belt' tool.
  • Sanitization: No specific client-side sanitization is described, as processing occurs on the service provider side.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 09:29 PM
Security Audit — agent-trust-hub — elevenlabs-sound-effects