dialogue-audio
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references installation guidelines located at a remote URL under the vendor's repository.
- Evidence:
https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.mdfound in SKILL.md. - [COMMAND_EXECUTION]: The skill instructs the user to perform authentication and run remote applications using a command-line interface tool.
- Evidence:
belt loginandbelt app runcommands are used throughout SKILL.md to interact with audio generation services. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided natural language prompts to generate audio content, which represents an injection surface.
- Ingestion points: The
promptfield within the JSON input for thefalai/dia-ttsapplication (SKILL.md). - Boundary markers: None present in the instructions.
- Capability inventory: The skill utilizes the
beltCLI to execute remote applications (SKILL.md). - Sanitization: No explicit sanitization or filtering of prompt content is mentioned.
Audit Metadata