dialogue-audio

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references installation instructions and related tools hosted on the inference-sh GitHub repository (github.com/inference-sh/skills).
  • [COMMAND_EXECUTION]: The skill relies on the belt CLI tool to execute remote audio generation and processing applications, such as falai/dia-tts and infsh/media-merger.
  • [INDIRECT_PROMPT_INJECTION]: The skill demonstrates an attack surface where instructions could be embedded in the data processed by the audio generation service.
  • Ingestion points: The prompt field within the JSON input for belt app run commands in SKILL.md examples.
  • Boundary markers: None identified; user input is directly interpolated into the command structure.
  • Capability inventory: The skill uses Bash(belt *) to interact with external APIs for text-to-speech and audio merging.
  • Sanitization: No explicit sanitization or input validation logic is present in the skill's instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 08:14 PM
Security Audit — agent-trust-hub — dialogue-audio