elevenlabs-dialogue
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
beltCLI via theBashtool to run dialogue generation apps such aselevenlabs/text-to-dialogue. - [EXTERNAL_DOWNLOADS]: The skill instructions include the installation of the
belt-sh/clipackage and link to installation documentation hosted on theinference-shGitHub repository. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text strings to generate audio, creating a surface for indirect prompt injection where instructions could be embedded in the dialogue text.
- Ingestion points: The
segmentsarray within the JSON input provided to thebeltcommand inSKILL.mdexamples. - Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present in the dialogue templates.
- Capability inventory: The skill utilizes the
Bashtool to execute local CLI commands. - Sanitization: No sanitization or validation of the input text is described in the documentation.
Audit Metadata