elevenlabs-dialogue
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references installation instructions and setup documentation from the service provider's public GitHub repository (inference-sh/skills). This is a standard practice for configuring the required CLI environment.
- [COMMAND_EXECUTION]: The skill instructs the agent to use the 'belt' CLI tool to run remote applications for text-to-dialogue generation, music generation, and media merging. These commands are restricted to the authorized 'belt' tool as specified in the frontmatter.
- [PROMPT_INJECTION]: The skill accepts user-supplied dialogue segments and interpolates them into JSON payloads for the CLI. While it lacks explicit boundary markers (e.g., specific delimiters for dialogue text) or sanitization instructions to prevent the agent from obeying instructions embedded within the dialogue, this represents an inherent risk profile for text-to-speech tools rather than a malicious implementation.
Audit Metadata