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.md found 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 login and belt app run commands 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 prompt field within the JSON input for the falai/dia-tts application (SKILL.md).
  • Boundary markers: None present in the instructions.
  • Capability inventory: The skill utilizes the belt CLI to execute remote applications (SKILL.md).
  • Sanitization: No explicit sanitization or filtering of prompt content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 09:29 PM
Security Audit — agent-trust-hub — dialogue-audio