elevenlabs-sound-effects
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches installation guidelines and related skills from the official inference-sh GitHub repository and the inference.sh domain.
- [COMMAND_EXECUTION]: Instructs the agent to use the
beltCLI for remote application execution and authentication. - [INDIRECT_PROMPT_INJECTION]: Processes untrusted text descriptions to generate audio effects, representing a potential injection surface.
- Ingestion points: The
textfield in thebelt app runcommand inputs within SKILL.md. - Boundary markers: Input parameters are encapsulated within JSON strings, providing structural separation.
- Capability inventory: The skill utilizes shell command execution (specifically limited to the
beltcommand) to communicate with external APIs. - Sanitization: There are no documented sanitization or filtering steps for the input text before it is passed to the generation tool.
Audit Metadata