dialogue-audio

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references a setup guide hosted on a public GitHub repository (inference-sh/skills).
  • [COMMAND_EXECUTION]: The skill requires the installation of the belt-sh/cli tool and executes commands using the belt CLI to interact with external APIs.
  • [REMOTE_CODE_EXECUTION]: The belt app run command is used to trigger remote model inference on the inference.sh and fal.ai platforms.
  • [PROMPT_INJECTION]: The skill accepts user-provided text for audio generation. Ingestion points: prompt field in input JSON in SKILL.md. Boundary markers: none. Capability inventory: belt app run command. Sanitization: none. This functionality is consistent with the primary purpose of the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 06:32 PM
Security Audit — agent-trust-hub — dialogue-audio