elevenlabs-dialogue
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the 'belt' CLI from the 'belt-sh' organization and references setup documentation hosted on the 'inference-sh' GitHub repository. These are necessary dependencies for the integration provided by the service.- [COMMAND_EXECUTION]: The skill provides numerous examples of using the 'belt' command-line tool via the 'Bash' capability to interact with the ElevenLabs API for dialogue generation.- [INDIRECT_PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection as it ingests structured text data for audio generation. Ingestion point: the 'segments' field in the JSON '--input' payload in SKILL.md. Boundary markers: delimited JSON structure. Capability inventory: Bash tool access to execute 'belt' commands. Sanitization: No specific input filtering or sanitization steps are described in the prompt instructions.
Audit Metadata