elevenlabs-dialogue
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill integrates with the official inference.sh platform to provide text-to-dialogue capabilities. All external references and tools are directly related to the platform's documented functionality.
- [EXTERNAL_DOWNLOADS]: References installation guidelines and configuration files from the official inference-sh organization on GitHub. These references are used for setup and documentation purposes.
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute 'belt' CLI commands for authenticating with the service and generating audio segments. These commands are necessary for the skill's primary function and operate within the expected scope of the tool.
- [SAFE]: The skill has a data ingestion surface for user-supplied text:
- Ingestion points: --input JSON block in SKILL.md.
- Boundary markers: None present.
- Capability inventory: Execution of 'belt' CLI via Bash tool.
- Sanitization: None specified. The indirect prompt injection risk is considered safe as the tool's output is limited to audio file generation.
Audit Metadata